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

Fernando Cañadas-Aránega; Francisco J. Mañas-Álvarez; José L- Guzmán; José C. Moreno; José L. Blanco-Claraco

cs.ROFeb 16, 2026

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

Authors: Fernando Cañadas-Aránega, Francisco J. Mañas-Álvarez, José L- Guzmán, José C. Moreno, José L. Blanco-Claraco

Organizations: Department of Informatics, CIESOL, ceiA3, Universidad de Almería, Ctra. Sacramento s/n, Almería, 04120, Spain · Department of Computer Science and Automation, National University of Distance Education (UNED), C/ Juan del Rosal 16, Madrid, 28040, Spain · Department of Engineering, CIESOL, ceiA3, Universidad de Almería, Ctra. Sacramento s/n, Almería, 04120, Spain

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 & tables

Panel of Figure 1 — Figure 1: Agroconnect greenhouse

Panel of Figure 2 — Figure 2: Agroconnect environment

Figure 3: Differential robot “Agricobiot I” in MVSim

Panel of Figure 4 — Figure 4: 3D model in the simulator

Figure 5: Soil type in the Agroconnect greenhouse

Figure 6: Distribution of greenhouse terrain sectors (in meters).

Terrain sector	Soil ( $s$ )	$\mu$	$C_{\mathrm{rr}}$	$C_{D}$
Gravel sand	1	0.2	0.10	1.25
Concrete	2	0.8	0.01	0.75
Compact sand	3	0.5	0.05	1.00

Table 1: Typical friction and rolling resistance coefficients for different terrain types ( Wong, 2022 ) .

Figure 7: Characterization of greenhouse terrain.

Figure 8: Low-level control scheme for motor $i\in\{R,L\}$ .

Figure 9: Mid-level control scheme. Low-level control is described in Figure 8 .

Figure 10: General high-level control scheme

Params	Value used	Params	Value used
$J$	2.22 kg m 2	$K_{P}$	70 N m s
$b$	0.75 N m s rad -1	$K_{I}$	40 N m
$k_{\tau}$	1 N m	$K_{aw}$	$K_{p}/K_{I}$ s -1
$K_{m}$	1.33 N m s rad -1	$\tau_{f}$	$K_{p}/K_{I}$ s
$\tau_{motor}$	2.97 s	$n_{f}$	1
$\tau_{max}$	$\pm$ 400 N m	$K_{ff}$	0.0

Table 2: Low-level control params

Figure 11: A reference robot stroke is defined for each category, with a predefined initial orientation and a randomly generated final orientation. The green dot corresponds to the robot’s initial pose, and points that follow category 2; the red arrow corresponds to the trajectory of category 1; the yellow arrow corresponds to the trajectory of category 2; the blue arrow corresponds to the trajectory of category 3; and the red cross corresponds to the target point for categories 2 and 3.

Figure 12: Category 1 test, with $m_{pl}=70$ , with slope on the ground and sector change

Figure 13: Category 2 test, low-level figure, with $m_{pl}=70$ , with slope in the terrain and change of sector

Figure 14: Category 2 test, mid-level figure, with $m_{pl}=70$ , with slope in the terrain and change of sector. The black box represents the moments before arriving at that area.

Figure 15: Rviz2 for category 3, where the local_costmap of TEB can be observed

Figure 16: Category 3 test, low-level figure, with $m_{pl}=70$ , with slope in the terrain and sector change

Figure 17: Category 3 test, mid-level figure, with $m_{pl}=70$ , with slope in the terrain and sector change. The black box represents the moments before arriving at that area.

Figure 18: Category 3 test, high-level figure, with $m_{pl}=70$ , with slope in the terrain and sector changer. The black box represents the moments before arriving at that area.

Figure 19: Rviz2 and MVSim for category 3, where the local_costmap of MPC can be observed in lighter shades and the global_costmap of the planner in darker shades.

		Low level	Mid level	High level
Terrain Conditions	Payload [kg]	$J_{1}$	$J_{2}$	$J_{3}$ = $SAE_{3}$	$J_{T_{3}}$
Slope OFF Change of terrain OFF	0	9.5080 $\pm$ 0.4513	88.0518 $\pm$ 4.2365	7.5235 $\pm$ 0.3628	35.0301 $\pm$ 1.6845
Slope OFF Change of terrain OFF	70	10.2158 $\pm$ 0.4897	89.7563 $\pm$ 4.3186	7.5824 $\pm$ 0.3691	35.8515 $\pm$ 1.7213
Slope ON Change of terrain OFF	0	11.1867 $\pm$ 0.5234	98.4242 $\pm$ 4.9186	7.7270 $\pm$ 0.3829	39.1172 $\pm$ 1.8927
Slope ON Change of terrain OFF	70	12.1946 $\pm$ 0.5713	101.2563 $\pm$ 5.0842	8.1245 $\pm$ 0.4018	40.5251 $\pm$ 1.9674
Slope OFF Change of terrain ON	0	9.3679 $\pm$ 0.4489	98.7567 $\pm$ 4.9012	6.5145 $\pm$ 0.3197	38.2173 $\pm$ 1.8431

Table 5: Average SAE and SCI with standard deviation of three tests in category 3 across all terrain and slope conditions

Robotic Control

Robotic control studies how machines use sensing and computation to produce reliable movement and interaction in changing environments.

See all 584 papers

Aug 29, 2026

Agri-Sim: Agricultural Simulation Platform for Embodied Intelligence Evaluation in Greenhouse Robotics

Agricultural-robot development requires simulation environments that can jointly support realistic scene construction, virtual sensing, autonomous navigation, motion planning, and manipulation-task execution. This paper presents Agri-Sim, a Unity and ROS2-based simulation platform for the closed-loop development and functional evaluation of agricultural robots. The platform contains a configurable tomato-greenhouse environment, a mobile dual-arm harvesting robot, virtual RGB-D, LiDAR, IMU, and joint sensors, and a bidirectional communication interface between Unity and ROS2. Unity is responsible for scene rendering, rigid-body dynamics, collision detection, virtual sensing, and task-state execution, whereas ROS2 and MoveIt 2 provide localization, navigation, collision-aware motion planning, inverse kinematics, and trajectory generation. Autonomous greenhouse navigation and dual-arm tomato harvesting were used to evaluate the complete simulation workflow. The experiments covered virtual sensor publication, ROS2-based navigation, collision-aware motion planning, mobile-base control, tomato acquisition, inter-arm handover, and box placement. The results demonstrate that Agri-Sim supports closed-loop integration and repeatable functional evaluation of navigation and manipulation workflows in a controlled virtual greenhouse, providing a practical foundation for subsequent algorithm development and Sim-to-Real studies.

Shuhan Shi, Zhenfeng Xue, Minghao Mei +3

School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China · Sino-European School of Technology of Shanghai University, Shanghai University, Shanghai 200444, China · School of Future Technology (Institute of Artificial Intelligence), Shanghai University, Shanghai 200444, China

Robotic Harvesting Robotics Simulation Agricultural Robotics Robotic Manipulation

Ask PDF

Jun 21, 2026

Integrated cloud-based architecture for robot-robot and human-robot collaboration using ROS 2--MQTT in Mediterranean Greenhouses

The imperative to develop more sustainable agriculture demands a transition from isolated automation toward the deployment of multi-robot systems (MRS) in agrifood environments. However, Mediterranean greenhouse settings-characterized by narrow corridors, dense biomass, and structural metallic interference-pose significant challenges for robust and scalable communication between agents. Traditional robotic frameworks, such as ROS 2, frequently encounter node discovery issues and latency spikes due to dynamic obstacles, dense foliage, and other characteristic greenhouse elements, creating a critical bottleneck for real-time coordination. This paper proposes an innovative cloud-based hybrid architecture that establishes a two-way communication bridge between ROS 2, acting as an edge computing platform, and iVeg as a Decision Support System (DSS), using MQTT and the European FIWARE platform. The proposed framework enables seamless interoperability between fleets of multiple robots in environments with communication constraints, facilitating the synchronised exchange of high-level telemetry, point cloud data and farmer identification for collaboration, amongst other critical data. The architecture was validated in a high-fidelity simulation environment and subsequently tested in a real-world greenhouse scenario, demonstrating its ability to maintain persistent connectivity and data integrity under adverse network conditions. The results indicate that the integration of MQTT effectively eliminates information silos, providing a scalable and decentralised solution for managing complex robotic missions, which are executed locally via Edge Computing. This work sets a new methodological precedent for the concept of Greenhouse Models as a Service (GMaaS), bridging the gap between low-level robotic control and high-level, cloud-based IoT decision-making.

F. Cañadas-Aránega, M. Muñoz, J. C. Moreno +1

Department of Informatics, CIESOL, ceiA3, Universidad de Almería, Ctra.2026 Sacramento s/n, Almería, 04120, Spain · Department of Engineering, CIESOL, ceiA3, Universidad de Almería, Ctra. Sacramento s/n, Almería, 04120, Spain

Robotics Multi-Robot Coordination Human-Robot Collaboration Agricultural Robotics Multi-Agent Communication

Ask PDF

May 24, 2026

GreenSeg: Ground Segmentation Algorithm for Agricultural Robots in Mediterranean Greenhouses using RGB-D Point Clouds

Greenhouse agriculture in the Mediterranean region faces significant automation challenges due to its unique structural and environmental constraints. These environments are characterized by extremely narrow aisles, heterogeneous terrains ranging from concrete to tilled soil and severe optical interference caused by polyethylene covers, which induce specular reflections and "ghost points" in depth sensors. While autonomous navigation is essential for digitizing agricultural tasks, traditional solutions often rely on expensive 3D LiDAR systems that are economically unscalable for most facilities. To address this, this paper presents GreenSeg, a robust perception framework for autonomous navigation using RGB-D sensing. The proposed method introduces a dual-layer validation strategy: a robust global plane fitting combined with a surface curvature filter for terrain adaptability, and a seed-point-based Region Growing constraint to ensure the spatial continuity of the navigable plane. Experimental validation was conducted using the AGRICOBIOT I platform across four diurnal scenarios with varying solar elevations. The results show that GreenSeg consistently outperforms benchmark segmentation methods, achieving peak improvements of 11.58% in mean Recall and 19.24% in mIoU during critical rotational maneuvers at the end of corridors. These findings confirm that the proposed algorithm enables stable and safe autonomous navigation in unstructured, dynamic agricultural environments that are subject to budget constraints and sensitive to lighting conditions.

Fernando Cañadas-Aránega, José C. Moreno, José L. Blanco-Claraco

Department of Informatics, CIESOL, ceiA3, Universidad de Almería, Ctra. Sacramento s/n, Almería, 04120, Spain · Department of Engineering, CIESOL, ceiA3, Universidad de Almería, Ctra. Sacramento s/n, Almería, 04120, Spain

3D Point Cloud Segmentation Robot Navigation Agricultural Robotics Robotic Perception Semantic Segmentation

Ask PDF

Abstract

Robotic Control

Explore similar work

Agri-Sim: Agricultural Simulation Platform for Embodied Intelligence Evaluation in Greenhouse Robotics

Integrated cloud-based architecture for robot-robot and human-robot collaboration using ROS 2--MQTT in Mediterranean Greenhouses

GreenSeg: Ground Segmentation Algorithm for Agricultural Robots in Mediterranean Greenhouses using RGB-D Point Clouds