A ROS2 Benchmarking Framework for Hierarchical Control Strategies in Mobile Robots for Mediterranean Greenhouses

TL;DR

This work tackles the lack of reproducible benchmarks for mobile robot control in agro-industrial settings by introducing a ROS2-compatible benchmarking framework that tightly couples a high-fidelity 3D Mediterranean greenhouse model with a physics-based simulator. It implements a hierarchical control stack (PID at the actuator level, MPC-TEB for trajectory tracking, and Lazy theta* for global planning) and evaluates them under three disturbance scenarios (payload, terrain type, and slope) using standardized metrics SAE and SCI across three categorized benchmarks. Key contributions include an open-source MVSim-based environment with a detailed greenhouse and robot model, a modular plug-in architecture for comparing classical, predictive, and planning-based strategies, and a robust evaluation protocol with repeated trials to ensure reproducibility. The framework aims to bridge simulation and real-world agro-industrial deployments, enabling fair comparisons and accelerating the development of robust autonomous farming robots with real-world relevance.

Abstract

Mobile robots operating in agroindustrial environments, such as Mediterranean greenhouses, are subject to challenging conditions, including uneven terrain, variable friction, payload changes, and terrain slopes, all of which significantly affect control performance and stability. Despite the increasing adoption of robotic platforms in agriculture, the lack of standardized, reproducible benchmarks impedes fair comparisons and systematic evaluations of control strategies under realistic operating conditions. This paper presents a comprehensive benchmarking framework for evaluating mobile robot controllers in greenhouse environments. The proposed framework integrates an accurate three dimensional model of the environment, a physics based simulator, and a hierarchical control architecture comprising low, mid, and high level control layers. Three benchmark categories are defined to enable modular assessment, ranging from actuator level control to full autonomous navigation. Additionally, three disturbance scenarios payload variation, terrain type, and slope are explicitly modeled to replicate real world agricultural conditions. To ensure objective and reproducible evaluation, standardized performance metrics are introduced, including the Squared Absolute Error (SAE), the Squared Control Input (SCI), and composite performance indices. Statistical analysis based on repeated trials is employed to mitigate the influence of sensor noise and environmental variability. The framework is further enhanced by a plugin based architecture that facilitates seamless integration of user defined controllers and planners. The proposed benchmark provides a robust and extensible tool for the quantitative comparison of classical, predictive, and planning based control strategies in realistic conditions, bridging the gap between simulation based analysis and real world agroindustrial applications.

Figures (19)

• Figure 1: Agroconnect greenhouse
• Figure 2: Agroconnect environment
• Figure 3: Differential robot "Agricobiot I" in MVSim
• Figure 4: 3D model in the simulator
• Figure 5: Soil type in the Agroconnect greenhouse