Towards a Unified Taxonomy of Agricultural Harvesting Technologies: Linking Physical Interaction, Automation, and Selectivity

Renato Cristiano Torres; Fabiano Mariath D Oliveira; Claudio Gottschalg Duque

cs.ROOct 9, 2026

Towards a Unified Taxonomy of Agricultural Harvesting Technologies: Linking Physical Interaction, Automation, and Selectivity

Authors: Renato Cristiano Torres, Fabiano Mariath D Oliveira, Claudio Gottschalg Duque

Organizations: Embrapa Agricultura Digital, Research Group on Scientific Computing, Information Engineering, and Automation, Campinas, Brazil · Embrapa, Information Technology Departament, Federal District, Brazill · University of Brasilia, Computational Linguistics, Federal District, Brazil

Abstract

Harvesting technologies have evolved from conventional mechanized systems based on bulk mechanical interaction toward increasingly automated and robotic systems capable of perception, decision-making, and localized actuation. This evolution has also created a classification problem, as harvesting systems are commonly described according to crop type, mechanical removal principle, sensing technology, robotic architecture, or degree of automation, making direct comparison difficult. This paper proposes a unified taxonomy for agricultural harvesting technologies based on two primary classification axes: the physical principle governing plant-machine interaction and the level of automation incorporated into the harvesting process. Selectivity is treated as an emergent functional attribute that expresses the biological and spatial scale at which perception and decision-making influence physical actuation. Conventional mechanized methods, including cutting, pulling, vibration, impact, brushing, pneumatic action, and combined systems, are analyzed together with semi-automated and robotic harvesting approaches. The analysis shows that increasing automation does not necessarily result in greater selectivity. A qualitative transition occurs when perception and decision-making directly influence product-level actuation, shifting harvesting from distributed or bulk interaction toward localized and selective manipulation. The proposed framework provides a common conceptual basis for positioning and comparing mechanized, automated, and robotic harvesting technologies. By separating the physical mechanism of product removal from the automation level and resulting selectivity, the taxonomy clarifies technological boundaries, identifies intermediate configurations, and supports the analysis and development of future harvesting systems.

Figures & tables

Reference	Physical interaction	Perception/robotics	Automation	Selectivity	Unified cross-domain taxonomy
Droukas et al. [ 7 ]	Partial	Strong	Strong	Partial	–
Kootstra et al. [ 24 ]	Partial	Strong	Strong	Strong	–
Pu [ 34 ]	Strong	Partial	Partial	Partial	–
Rajendran et al. [ 35 ]	Partial	Strong	Strong	Strong	–
Zhang [ 43 ]	Partial	Strong	Strong	Strong	–
Present framework	Strong	Strong	Strong	Explicit attribute	✓

Table 1: Primary emphasis of representative harvesting reviews and the integrative scope of the present framework. “Partial” indicates that the dimension is discussed but is not the principal organizing axis of the review.

Requirement	Representative range or condition reported in the literature	References
Terrain slope	Lower than approximately 12–15%, supporting machine stability and operational safety	[ 1 , 8 , 22 , 29 , 30 , 32 , 42 ]
Row spacing	Crop-dependent spacing allowing adequate machine traffic and harvesting operation	[ 4 , 9 , 22 ]
Plant spacing	Approximately 0.5–0.7 m in reported applications requiring compatibility between plant size and mechanized systems; not a general limitation for grain and seed harvesting	[ 12 , 22 , 39 ]
Obstacles between rows	Removal or management of stones, stumps, crop residues, and other obstacles that may interfere with machine displacement	[ 13 , 22 , 23 , 39 , 40 ]
Planting row length	Long rows are generally advantageous because they reduce turning maneuvers and improve operational efficiency	[ 22 , 23 , 39 ]
Headland width	Approximately 6.0 m in reported cases to allow machine maneuvering	[ 9 , 22 , 23 , 39 ]

Table 2: Representative production-system requirements reported for mechanized harvesting.

Figure 1: Conceptual transition from conventional bulk harvesting to selective product-level harvesting. Increasing automation alone does not guarantee selectivity; the decisive transition occurs when perception and decision-making govern localized actuation. Source: authors’ conceptual synthesis.

Method	Physical principle	Typical crops	References
Cutting	Product separation by mechanical shearing of the stem or entire plant	Grains and seeds (wheat, rice), sugarcane, forage crops	[ 22 , 37 , 39 ]
Pulling	Product removal by tensile force between plant and soil	Roots and tubers (potato, carrot, beetroot)	[ 39 ]
Vibration	Mechanical excitation used to detach the product from the plant	Woody crops (coffee), fruit crops (citrus, olive)	[ 8 , 10 , 34 ]
Impact	Transfer of kinetic energy through repeated impacts	Woody and industrial fruit crops (coffee, olive)	[ 10 , 22 , 34 ]
Brushing	Continuous mechanical contact using flexible elements	Fruit and woody crops under specific production systems	[ 8 , 10 , 15 ]
Pneumatic	Pressure differentials and airflow used for capture or transport	Seeds, lightweight fruits, auxiliary harvesting systems	[ 22 , 34 , 39 ]

Table 3: Mechanized harvesting methods according to physical interaction principle and typical crops.

Method	Physical principle and automation function	Typical crops	References
Selective grasping	Controlled mechanical force applied by robotic manipulators based on perception of the target product	Apple, orange, strawberry, tomato, bell pepper	[ 4 , 19 , 43 ]
Selective cutting	Localized cutting of the peduncle using automated blades or actuators	Lettuce, broccoli, high-value fruit crops	[ 34 , 43 ]
Assisted suction	Pressure differentials used for capture and transport, combined with visual perception	Strawberry, seeds, seedlings, light products	[ 34 , 43 ]
Semi-automated vibration	Mechanical excitation whose parameters are adjusted automatically using sensors and control algorithms	Citrus, olive, woody crops	[ 8 , 34 ]
Human–robot collaboration	Physical and cognitive interaction with task sharing between human operators and automated systems	Horticultural and fruit crops	[ 4 , 15 , 36 ]
Automated harvesting platforms	Automated navigation and operator assistance integrated with harvesting operations	Horticultural and fruit crops	[ 4 , 20 , 34 , 44 ]

Table 4: Automated and robotic harvesting approaches according to physical interaction principle.

Class	Description	Typical selectivity	References
Mechanization (no automation)	Harvesting execution based on mechanical energy; perception, decision-making, and control performed by the operator	Low	[ 12 , 22 , 39 ]
Automated navigation	Automation limited mainly to machine guidance and displacement while the underlying harvesting method remains mechanized	Low	[ 9 , 22 , 33 ]
Automated control	Automatic adjustment of harvesting parameters such as height, speed, or vibration without individual product selection	Low to medium	[ 9 , 11 , 39 ]
Semi-automated harvesting	Partial product selection based on automated perception with human intervention in decision-making or execution	Medium	[ 4 , 36 , 34 ]
Autonomous robotic harvesting	Integration of perception, decision-making, planning, and actuation in an automated harvesting system	High	[ 4 , 16 , 26 , 38 , 41 , 43 ]
Human–robot collaborative harvesting	Dynamic task sharing between human operators and automated or robotic systems	Variable	[ 4 , 15 , 36 ]

Table 5: Automation classes in agricultural harvesting and their typical selectivity.

Physical interaction	Mechanized	Auto. nav./control	Semi-auto.	Autonomous	Typical selectivity	Representative refs.
Cutting	$\checkmark$	$\checkmark$	$\checkmark$	$\checkmark$	Low–high	[ 22 , 34 , 43 ]
Pulling	$\checkmark$	$\checkmark$	–	–	Low–medium	[ 39 ]
Vibration	$\checkmark$	$\checkmark$	$\checkmark$	–	Low–medium	[ 8 , 10 , 34 ]
Impact	$\checkmark$	$\checkmark$	–	–	Low	[ 10 , 22 , 34 ]
Brushing	$\checkmark$	$\checkmark$	–	–	Low–medium	[ 8 , 10 , 15 ]
Pneumatic/suction	$\checkmark$	$\checkmark$	$\checkmark$	$\checkmark$	Low–high	[ 22 , 34 , 43 ]

Table 6: Conceptual matrix combining physical interaction and automation level. Check marks indicate combinations represented or directly supported by the harvesting approaches discussed in the reviewed literature; a dash indicates that the combination is not established by the present review.

Robotic Harvesting

See all 22 papers

CLASP: A Cluster-Level Autonomous Selective Picking Robot with a Soft Rolling-Band Gripper for Fresh-Market Blueberry Harvesting
Sep 16, 2026Yixuan Xia, Yilin Cai, Natalia Belen Espinoza +4Robotic Grasping Force-Controlled Robotic Manipulation
George W. Woodruff School of Mechanical Engineering, Georgia Institute of Technology, Atlanta, GA 30332 USA · Department of Crop & Soil Sciences, University of Georgia, Athens, GA 30605, USA · Bio-Sensing, Automation, and Intelligence Laboratory, Department of Agricultural and Biological Engineering, University of Florida, Gainesville, Florida 32611, USA +3
Learning What Can Be Picked: Active Reachability Estimation for Efficient Robotic Fruit Harvesting
Mar 24, 2026Nur Afsa Syeda, Mohamed Elmahallawy, Luis Fernando de la Torre +1Agricultural Robotics Robotic Harvesting
Washington State University, Richland, WA 99354, USA
FruitTouch: A Perceptive Gripper for Gentle and Scalable Fruit Harvesting
Feb 22, 2026Ruohan Zhang, Mohammad Amin Mirzaee, Wenzhen YuanRobotic Grasping Robotic Hand Design
University of Illinois at Urbana-Champaign, Champaign, IL, USA

Sep 16, 2026J/K move · Enter open · S save

CLASP: A Cluster-Level Autonomous Selective Picking Robot with a Soft Rolling-Band Gripper for Fresh-Market Blueberry Harvesting

Yixuan Xia, Yilin Cai, Natalia Belen Espinoza, Changying Li+3

George W. Woodruff School of Mechanical Engineering, Georgia Institute of Technology, Atlanta, GA 30332 USA · Department of Crop & Soil Sciences, University of Georgia, Athens, GA 30605, USA · Bio-Sensing, Automation, and Intelligence Laboratory, Department of Agricultural and Biological Engineering, University of Florida, Gainesville, Florida 32611, USA+3

Robotic Grasping Force-Controlled Robotic Manipulation Agricultural Robotics Soft Robotics Robotic Harvesting

Open paper AskPDF arXiv

Fresh-market blueberries require selective, gentle picking, which is labor-intensive and expensive. Over-the-row machine harvesters are fast but non-selective, bruising mixed-ripeness fruit and limiting yield to the processing market. Selective robotic harvesters typically target individual fruits rather than fruit clusters, which limits harvesting efficiency for small, densely clustered blueberries. This paper presents CLASP, a Cluster-Level Autonomous Selective Picking robot with a Soft Active Rolling-Band Gripper (SARB-Gripper). Two compliant bands envelop the cluster and roll against the fruit, drawing mature berries off in sequence, while closed-loop regulation of the pulling force keeps the applied load below the immature detachment threshold. A global-to-local perception pipeline pairs an eye-to-hand camera for global cluster detection and target selection with an eye-in-hand camera for local localization and cluster orientation estimation. Field measurements confirm a clear detachment-force separation between mature and immature fruit, and the SARB-Gripper reproduces a commanded pulling force to within \SI{3.7}{\percent}, enabling selective harvesting at the cluster level. In end-to-end field trials, CLASP autonomously grasped 23 of 25 presented clusters (\SI{92}{\percent}). With the component cost of approximately $3326 per unit, CLASP offers a scalable approach to selective cluster-level harvesting for fresh-market blueberries.

Abstract

Robotic Harvesting

Explore similar work

CLASP: A Cluster-Level Autonomous Selective Picking Robot with a Soft Rolling-Band Gripper for Fresh-Market Blueberry Harvesting

Learning What Can Be Picked: Active Reachability Estimation for Efficient Robotic Fruit Harvesting

FruitTouch: A Perceptive Gripper for Gentle and Scalable Fruit Harvesting