A reinforcement learning-enhanced multi-objective iterated greedy algorithm for weeding-robot operation scheduling problems

•We propose a population-based iterated greedy algorithm enhanced with Q-learning for a multi-weeding-robots operation scheduling problem.•An problem-related IBH is designed to generate a set of initial solutions and a local search based on the high-load robot and the critical robot is proposed.•An...

Full description

Saved in:

Bibliographic Details
Published in:	Expert systems with applications Vol. 263; p. 125760
Main Authors:	Miao, Zhonghua, Guo, Hengwei, Pan, Quan-ke, Peng, Chen, Xu, Ziyu
Format:	Journal Article
Language:	English
Published:	Elsevier Ltd 05.03.2025
Subjects:	Iterated greedy algorithm Multi-objective optimization Operation scheduling Q-learning Smart farms Task allocation Operation scheduling Q-learning Iterated greedy algorithm Multi-objective optimization Smart farms Task allocation
ISSN:	0957-4174
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	•We propose a population-based iterated greedy algorithm enhanced with Q-learning for a multi-weeding-robots operation scheduling problem.•An problem-related IBH is designed to generate a set of initial solutions and a local search based on the high-load robot and the critical robot is proposed.•An effective destruction phase is developed, based on the adaptive destruction intensity and Q-learning framework.•Experimental results demonstrate the effectiveness of the Q_DPIG based on the test datasets and a real case study from a farmland management center. With technological advancements, robots have been widely used in various fields and play a vital role in the production execution system of a smart farm. However, the operation scheduling problem of robots within production execution systems has not received much attention so far. To enable efficient management, this paper develops a multi-objective mathematical model concerning both the efficiency and economic indicators. We propose a population-based iterated greedy algorithm enhanced with Q-learning (Q_DPIG) for a multi-weeding-robots operation scheduling problem. An index-based heuristic (IBH) is designed to generate a diverse set of initial solutions, while an adaptive destruction phase, guided by the Q-learning framework, ensures effective neighborhood search and solution optimization. Additionally, a local search method focusing on the high-load and the critical robots is employed to further optimize the two objectives. Finally, Q_DPIG is demonstrated to be effective and significantly outperform the state-of-the-art algorithms through comprehensive test datasets and a real case study from a farmland management center.
ISSN:	0957-4174
DOI:	10.1016/j.eswa.2024.125760