Agriculture fleet vehicle routing: A decentralised and dynamic problem

Abstract

To date, the research on agriculture vehicles in general and Agriculture Mobile Robots (AMRs) in particular has focused on a single vehicle (robot) and its agriculture-specific capabilities. Very little work has explored the coordination of fleets of such vehicles in the daily execution of farming tasks. This is especially the case when considering overall fleet performance, its efficiency and scalability in the context of highly automated agriculture vehicles that perform tasks throughout multiple fields potentially owned by different farmers and/or enterprises. The potential impact of automating AMR fleet coordination on commercial agriculture is immense. Major conglomerates with large and heterogeneous fleets of agriculture vehicles could operate on huge land areas without human operators to effect precision farming. In this paper, we propose the Agriculture Fleet Vehicle Routing Problem (AF-VRP) which, to the best of our knowledge, differs from any other version of the Vehicle Routing Problem studied so far. We focus on the dynamic and decentralised version of this problem applicable in environments involving multiple agriculture machinery and farm owners where concepts of fairness and equity must be considered. Such a problem combines three related problems: the dynamic assignment problem, the dynamic 3-index assignment problem and the capacitated arc routing problem. We review the state-of-the-art and categorise solution approaches as centralised, distributed and decentralised, based on the underlining decision-making context. Finally, we discuss open challenges in applying distributed and decentralised coordination approaches to this problem.

Big Data Management Algorithms, Deep Learning-Based Object Detection Technologies, and Geospatial Simulation and Sensor Fusion Tools in the Internet of Robotic Things

“…Digital twinbased product development, virtual data analytics, machining process monitoring [77][78][79][80], and performance prediction tools articulate industrial robotic networks. Intelligent manufacturing environments and cyber-physical production systems [81][82][83][84] develop on decision-making process automation [85][86][87][88], digital twin and cloud computing technologies, and smart infrastructure sensors. Machine and reinforcement learning algorithms and distributed wireless sensor networks [89][90][91][92] articulate autonomous routing decisions and enhance big data scalability.…”

“…[ [85][86][87][88] IoRT devices accurately process and analyze collected data by deploying image recognition technology, geospatial simulation and sensor fusion tools, and intelligent optimization algorithms. [89][90][91][92] Robot-based assistance of IoT-enabled edge computing technologies requires blockchain-enabled edge computing systems, heterogeneous computational collective intelligence and processes, and distributed edge devices and algorithms.…”

“…Routing efficiency and scalability of mobile robots can be achieved through autonomous robot coordination in dynamic decentralized environments and across wireless wearable sensor networks [85][86][87][88] by integrating blockchain technologies, remote sensing environmental data, and sensor-based deep learning techniques. Industrial cloud robotics develops on preventive maintenance scheduling, product condition monitoring, data-driven planning technologies, and augmented reality algorithms.…”

“…Our specific contribution is to clarify how mobile connected IoRT devices [73][74][75][76], cloud and pattern recognition technologies, networked robotics, and automated machines [77][78][79][80] configure autonomous manufacturing units in dynamic simulation environments in terms of robotic behavior control, sensor and actuator interconnections, and real-time data processing and analysis [81][82][83][84]. Correlations with previously published literature comprise analyses on how industrial cloud robotics integrates autonomous production systems, smart manufacturing task management [85][86][87][88], simulation optimization algorithms, and data visualization tools, while disparities encompass our integration of the sources on how autonomous robotized devices develop on virtual simulation tools, real-time monitoring capabilities [89][90][91][92], data fusion techniques, and cloud computing algorithms. The research problems are whether computer vision techniques, geospatial data mining [93][94][95][96], simulation-based digital twins, and real-time monitoring technology [97][98][99][100] optimize remote sensing robots [101][102][103][104][105].…”

Towards Agrirobot Digital Twins: Agri-RO5—A Multi-Agent Architecture for Dynamic Fleet Simulation

“…The Agri-RO5 architecture includes advanced simulation tools to tackle the intricate agriculture fleet vehicle routing problem (AF-VRP) in rural areas with low connectivity. AF-VRP considers both dynamic task assignment and vehicle routing, as presented in [2].…”