The increasing labor costs in agriculture have accelerated the adoption of multirobot systems for orchard harvesting. However, efficiently coordinating these systems is challenging due to the complex interplay between makespan and energy consumption, particularly under practical constraints like load-dependent speed variations and battery limitations. This article defines the multiobjective agricultural multielectrical-robot task allocation (AMERTA) problem, which systematically incorporates these often-overlooked real-world constraints. To address this problem, we propose a hybrid hierarchical route reconstruction algorithm (HRRA) that integrates several innovative mechanisms, including a hierarchical encoding structure, a dual-phase initialization method, task-sequence optimizers, and specialized route reconstruction operators. Extensive experiments on 45 test instances demonstrate HRRA’s superior performance against seven state-of-the-art algorithms. Statistical analysis, including the Wilcoxon signed-rank and Friedman tests, empirically validates HRRA’s competitiveness and its unique ability to explore previously inaccessible regions of the solution space. In general, this research contributes to the theoretical understanding of multirobot coordination by offering a novel problem formulation and an effective algorithm, thereby also providing practical insights for agricultural automation.

Strawberries naturally grow in clusters, interwoven with leaves, stems, and other fruits, which frequently leads to occlusion. This inherent growth habit presents a significant challenge for robotic picking, as traditional percept-plan-control systems struggle to reach fruits amid the clutter. Effectively picking an occluded strawberry demands dexterous manipulation to carefully bypass or gently move the surrounding soft objects and precisely access the ideal picking point located at the stem just above the calyx. To address this challenge, we introduce a strawberry-picking robotic system that learns from human demonstrations. Our system features a 4-DoF SCARA arm paired with a human teleoperation interface for efficient data collection and leverages an End Pose Assisted Action Chunking Transformer (ACT) to develop a fine-grained visuomotor picking policy. Experiments under various occlusion scenarios demonstrate that our modified approach significantly outperforms the direct implementation of ACT, underscoring its potential for practical application in occluded strawberry picking.

The continuous innovation of smart robotic technologies is driving the development of smart orchards, enhancing the potential for automated harvesting systems. While multi-robot systems offer promising solutions to address labor shortages and rising costs, the efficient scheduling of these systems presents complex optimization challenges. This research investigates the multi-trip picking robot task scheduling (MTPRTS) problem. The problem is characterized by allowing robot redeployment while adhering to strict makespan constraints, which encompasses the interdependencies among robot weight, robot load, and energy consumption, thereby introducing substantial computational challenges. Despite the critical role of local search in vehicle routing problems, most existing algorithms are hampered by redundant local operations, leading to search inefficiency and premature convergence, particularly in large-scale scenarios. To address these limitations, we propose an adaptive experience-based discrete genetic algorithm (AEDGA) that introduces three key innovations: (1) an integrated load-distance balancing initialization method, (2) a clustering-based local search mechanism, and (3) an experience-based adaptive selection strategy. To ensure solution feasibility under makespan constraints, we develop a solution repair strategy implemented through three distinct frameworks. Comprehensive experiments on 18 newly generated instances and 24 existing benchmarks demonstrate that AEDGA significantly outperforms six state-of-the-art algorithms.

High-resolution yield maps for manually harvested crops are impractical to generate on commercial scales because yield monitors are available only for mechanical harvesters. However, precision crop management relies on accurately determining spatial and temporal yield variability. This study presents the development of an integrated system for precision yield estimation and mapping for manually harvested strawberries. Conventional strawberry picking carts were instrumented with a Global Positioning System (GPS) receiver, an Inertial Measurement Unit (IMU), and load cells to record real-time geo-tagged harvest data and cart motion. Extensive data were collected in two strawberry fields in California, USA, during a harvest season. To address the inconsistencies and errors caused by the sensors and the manual harvesting process, a robust data processing pipeline was developed by integrating supervised deep learning model with unsupervised algorithms. The pipeline was used to estimate the yield distribution and generate yield maps for season-long harvests at the desired grid resolution. The estimated yield distributions were used to calculate two metrics: the total mass harvested over specific row segments and the total mass of trays harvested. The metrics were compared to ground truth and achieved accuracies of 90.48% and 94.05%, respectively. Additionally, the accuracy of the estimated yield based on the number of trays harvested per cart for season-long harvest was better than 94% achieving a strong correlation (Pearson r = 0.99) with the actual number of counted trays in both fields. The proposed system provides a scalable and practical solution for specialty crops, assisting in efficient yield estimation and mapping, field management, and labor management for sustainable crop production. The dataset and code supporting this study are available at: https://doi.org/10.5061/dryad.v6wwpzh7h and https://github.com/uddhavbhattarai/iCarritoYieldEstimationandMapping.git.

Ground robots often carry payloads, implements, or other attachments that turn their effective footprint into complex, non-convex shapes. Navigating safely through clutter then requires reasoning about this true geometry, yet most local planners simplify it with convex or inflated proxies and rasterize sensor data into occupancy grids or distance fields. Both choices eliminate feasible motions when clearance is comparable to the footprint geometry. We present EXACT-MPPI, a training-free local navigation framework that maps local point-cloud observations and sparse guidance directly to motion commands, without any intermediate map representation. The framework embeds an analytic, exact signed-distance evaluator into a Model Predictive Path Integral (MPPI) controller. The footprint is represented as a simple polygon for general convex or concave planar shapes, with a rectangle-cover specialization for faster evaluation of rectilinear footprints, enabling footprint-aware collision costs without convex decomposition, inflation, or learned encoders. During each MPPI rollout, observed obstacle points are transformed into the predicted body frame and evaluated against the footprint. All operations are batched in JAX, leveraging GPU parallelism for real-time receding-horizon control. Experiments show that EXACT-MPPI accelerates batched distance evaluation over a learned point-to-robot baseline, preserves feasible motion where convex-footprint planners fail, and remains robust under dense static and moving obstacles. The same framework deploys on differential-drive, Ackermann, omnidirectional, and hybrid-mode platforms by changing only the footprint description and motion model without per-platform training. Pairing exact footprint geometry with sampling-based predictive control thus offers a practical, training-free path to footprint-aware local navigation across diverse robots.

Multi-robot systems have emerged as a key technology for addressing the efficiency and cost challenges in labor-intensive industries. In the representative scenario of smart farming, planning efficient harvesting schedules for a fleet of electric robots presents a highly challenging frontier problem. The complexity arises not only from the need to find Pareto-optimal solutions for the conflicting objectives of makespan and transportation cost, but also from the necessity to simultaneously manage payload constraints and finite battery capacity. When robot loads are dynamically updated during planned multi-trip operations, a mandatory recharge triggered by energy constraints introduces an unscheduled load reset. This interaction creates a complex cascading effect that disrupts the entire schedule and renders traditional optimization methods ineffective. To address this challenge, this paper proposes the segment anchoring-based balancing algorithm (SABA). The core of SABA lies in the organic combination of two synergistic mechanisms: the sequential anchoring and balancing mechanism, which leverages charging decisions as `anchors' to systematically reconstruct disrupted routes, while the proportional splitting-based rebalancing mechanism is responsible for the fine-grained balancing and tuning of the final solutions' makespans. Extensive comparative experiments, conducted on a real-world case study and a suite of benchmark instances, demonstrate that SABA comprehensively outperforms 6 state-of-the-art algorithms in terms of both solution convergence and diversity. This research provides a novel theoretical perspective and an effective solution for the multi-robot task allocation problem under energy constraints.

Autonomous agricultural vehicles (AAVs), including field robots and autonomous tractors, are becoming essential in modern farming by improving efficiency and reducing labor costs. A critical task in AAV operations is headland turning between crop rows. This task is challenging in orchards with limited headland space, irregular boundaries, operational constraints, and static obstacles. While traditional trajectory planning methods work well in arable farming, they often fail in cluttered orchard environments. This letter presents a novel trajectory planner that enhances the safety and efficiency of AAV headland maneuvers, leveraging advancements in autonomous driving. Our approach includes an efficient front-end algorithm and a high-performance back-end optimization. Applied to vehicles with various implements, it outperforms state-of-the-art methods in both standard and challenging orchard fields. This work bridges agricultural and autonomous driving technologies, facilitating a broader adoption of AAVs in complex orchards.

The strawberry farming is labor-intensive, particularly in tasks requiring dexterous manipulation such as picking occluded strawberries. To address this challenge, we present the Strawberry Robotic Operation Interface (SROI), an open-source device designed for collecting dexterous manipulation data in robotic strawberry farming. The SROI features a handheld unit with a modular end effector, a stereo robotic camera, enabling the easy collection of demonstration data in field environments. A data post-processing pipeline is introduced to extract spatial trajectories and gripper states from the collected data. Additionally, we release an open-source dataset of strawberry picking demonstrations to facilitate research in dexterous robotic manipulation. The SROI represents a step toward automating complex strawberry farming tasks, reducing reliance on manual labor.

Plant factory cultivation is widely recognized for its ability to optimize resource use and boost crop yields. To further increase the efficiency in these environments, we propose a mixed-integer linear programming (MILP) framework that systematically schedules and coordinates dual-arm harvesting tasks, minimizing the overall harvesting makespan based on pre-mapped fruit locations. Specifically, we focus on a specialized dual-arm harvesting robot and employ pose coverage analysis of its end effector to maximize picking reachability. Additionally, we compare the performance of the dual-arm configuration with that of a single-arm vehicle, demonstrating that the dual-arm system can nearly double efficiency when fruit densities are roughly equal on both sides. Extensive simulations show a 10-20% increase in throughput and a significant reduction in the number of stops compared to non-optimized methods. These results underscore the advantages of an optimal scheduling approach in improving the scalability and efficiency of robotic harvesting in plant factories.

Headland maneuvering is a crucial aspect of unmanned field operations for autonomous agricultural vehicles (AAVs). While motion planning for headland turning in open fields has been extensively studied and integrated into commercial auto-guidance systems, the existing methods primarily address scenarios with ample headland space and thus may not work in more constrained headland geometries. Commercial orchards often contain narrow and irregularly shaped headlands, which may include static obstacles,rendering the task of planning a smooth and collision-free turning trajectory difficult. To address this challenge, we propose an optimization-based motion planning algorithm for headland turning under geometrical constraints imposed by field geometry and obstacles.

Solar energy is known as the most primitive source of energy; it's clean, renewable, abundant, and widely distributed, offering a very broad prospect for utilization. However, the low efficiency of solar energy utilization has always been affecting and hindering the popularization of solar energy technology. The design of a solar tracking system offers a new approach to solving this problem, thereby greatly improving the efficiency of solar energy utilization. This design employs a photoelectric tracking method, using a stepper motor driven by photoelectric sensors, which generate feedback signals to a microprocessor based on the intensity of incident light. The microprocessor runs the program and controls the tracking mechanism to adjust the angle of the solar panels to track the sun. A single-chip microcontroller-implemented solar tracking system can effectively improve the photoelectric conversion efficiency of solar panels and has a broad application prospect.

IntroductionEstimating and understanding the yield variability within an individual field is critical for precision agriculture resource management of high value tree crops. Recent advancements in sensor technologies and machine learning make it possible to monitor orchards at very high spatial resolution and estimate yield at individual tree level.MethodsThis study evaluates the potential of utilizing deep learning methods to predict tree-level almond yield with multi-spectral imagery. We focused on an almond orchard with the ‘Independence’ cultivar in California, where individual tree harvesting and yield monitoring was conducted for ~2,000 trees and summer aerial imagery at 30cm was acquired for four spectral bands in 2021. We developed a Convolutional Neural Network (CNN) model with a spatial attention module to take the multi-spectral reflectance imagery directly for almond fresh weight estimation at the tree level.ResultsThe deep learning model was shown to predict the tree level yield very well, with a R2 of 0.96 (±0.002) and Normalized Root Mean Square Error (NRMSE) of 6.6% (±0.2%), based on 5-fold cross validation. The CNN estimation captured well the patterns of yield variation between orchard rows, along the transects, and from tree to tree, when compared to the harvest data. The reflectance at the red edge band was found to play the most important role in the CNN yield estimation.DiscussionThis study demonstrates the significant improvement of deep learning over traditional linear regression and machine learning methods for accurate and robust tree level yield estimation, highlighting the potential for data-driven site-specific resource management to ensure agriculture sustainability.

GPS-based navigation in orchards can be unstable because trees may block the GPS signal or introduce multipath errors. Most research on robot navigation without GPS has focused on guidance inside orchard rows; end-of-row detection has not received enough attention. Additionally, navigation between rows relies on reference maps or artificial landmarks. In this work, a novel row-end detection method is presented, which detects drastic changes in the statistical distribution of the sensed point cloud as the robot gets closer to the row’s end. A row-entry method was also implemented that builds a local map that is used by a reactive path tracker. The system was evaluated in a 24-row block in a vineyard. Once the robot was closer than 7 m from the end of a row, the algorithm detected it with a 100% success rate and calculated the distance from it with a mean error of 0.54 m. The system was also evaluated in vineyard configurations with parallel and slanted vine rows in consecutive blocks. The system worked well in all configurations, except where the next block had rows aligned to the rows of the current block and the headland width was closer than 5 m.

The cover image is based on the Research Article A strawberry harvest-aiding system with crop-transport collaborative robots: Design, development, and field evaluation by Chen Peng et al., https://doi.org/10.1002/rob.22106.

Mechanizing the manual harvesting of fresh market fruits constitutes one of the biggest challenges to the sustainability of the fruit industry. During manual harvesting of some fresh‐market crops like strawberries and table grapes, pickers spend significant amounts of time walking to carry full trays to a collection station at the edge of the field. A step toward increasing harvest automation for such crops is to deploy harvest‐aid collaborative robots (co‐bots) that transport empty and full trays, thus increasing harvest efficiency by reducing pickers' non‐productive walking times. This study presents the development of a co‐robotic harvest‐aid system and its evaluation during commercial strawberry harvesting. At the heart of the system lies a predictive stochastic scheduling algorithm that minimizes the expected non‐picking time, thus maximizing the harvest efficiency. During the evaluation experiments, the co‐robots improved the mean harvesting efficiency by around 10% and reduced the mean non‐productive time by 60%, when the robot‐to‐picker ratio was 1:3. The concepts developed in this study can be applied to robotic harvest‐aids for other manually harvested crops that involve walking for crop transportation.

A robust navigation system is a prerequisite for a mobile robotic platform to carry out precision agriculture tasks in a modern orchard. In contrast to open fields, navigation based solely on the Global Navigation Satellite System (GNSS) is not stable in many orchards, where tree canopies may block the GNSS signal or introduce multipath. Many works have been done to localize the robot while traversing the inside a row, but navigating the robot to the next row on headland still relies on a reference map or artificial landmarks. In this work, we developed a row end detection method by exploiting drastic changes in the statistical distribution of points sensed by a depth camera compared to the points inside the row. Also, a robust way of row entry method is implemented by building a local environment map and reactive path tracker. The whole navigation system is tested and evaluated on a mobile robot in a vineyard. The experiment results show the robot can detect the tree row-end accurately and maneuver a U-turn to the next row safely.

Mechanizing the manual harvesting of fresh market fruits constitutes one of the biggest challenges to the sustainability of the fruit industry. During manual harvesting of some fresh-market crops like strawberries and table grapes, pickers spend significant amounts of time walking to carry full trays to a collection station at the edge of the field. A step toward increasing harvest automation for such crops is to deploy harvest-aid collaborative robots (co-bots) that transport the empty and full trays, thus increasing harvest efficiency by reducing pickers' non-productive walking times. This work presents the development of a co-robotic harvest-aid system and its evaluation during commercial strawberry harvesting. At the heart of the system lies a predictive stochastic scheduling algorithm that minimizes the expected non-picking time, thus maximizing the harvest efficiency. During the evaluation experiments, the co-robots improved the mean harvesting efficiency by around 10% and reduced the mean non-productive time by 60%, when the robot-to-picker ratio was 1:3. The concepts developed in this work can be applied to robotic harvest-aids for other manually harvested crops that involve walking for crop transportation.

Some specialty crops, such as strawberries and table grapes, are harvested by large crews of pickers who spend significant amounts of time carrying empty and full (with the harvested crop) trays. A step toward increasing harvest automation for such crops is to deploy harvest-aid robots that transport the empty and full trays, thus increasing harvest efficiency by reducing pickers' non-productive walking times. To that end, this work addresses human-robot collaboration modeling in a harvesting context. First, a modeling framework for all-manual and robot-aided harvesting was developed, which can be used for off-line simulation by system designers, but also as a representation model for robot control, during real-time operation. To serve both functions, the framework utilizes hybrid systems to model picker and robot activities. Finite state machines model discrete operating states, and difference equations describe motion and mass transfer within each discrete state. To capture the variability in human behavior and performance during harvesting, the human activity model utilizes stochastic parameters (e.g., picking time, walking speed) that can be estimated by measurements during harvesting. The stochastic model does not require direct yield measurements, which are not available for most specialty crops. Second, a stochastic simulator was developed based on the developed model. For a given field and crew size, the simulator samples all stochastic parameters to generate many instances of the harvest operation, and estimates metrics such as pickers' non-productive time and harvest operation efficiency. Part II of this work presents the calibration and evaluation of the simulator based on field data, and a case study that evaluates the effect of various robot scheduling algorithms on harvest efficiency.

Harvest-aid robots that transport empty and full trays during manual harvesting of specialty crops such as strawberries or table grapes can increase harvest efficiency, by reducing pickers' non-productive walking times. In Part I of this work, a modeling framework, and a stochastic simulator were presented for all-manual and robot-aided harvesting. This paper reports Part II of our work, which utilized data gathered in two strawberry fields during harvesting, to estimate the stochastic parameters involved in modeling pickers, and evaluate the prediction accuracy of the simulator for all-manual picking. Then, as a case study, non-productive time and harvest efficiency were estimated for robot-aided harvesting, for various picker-robot ratios and three priority-based reactive dispatching strategies for the robots. The simulator predicted the pickers' non-productive time during all-manual harvesting, with 6.4%, 3%, and 1.2% errors for the morning, afternoon, and "all-day" harvesting shifts, respectively. Statistical testing verified that predicted non-productive times followed the same distributions as the measured non-productive times (5% significance level). Simulations robustness was assessed by using morning data to simulate afternoon harvesting and vice-versa: non-productive times distributions were predicted accurately (10% significance level). Robot-aided simulation results - using the calibrated simulator for a 25-picker crew - showed that all-manual harvest efficiencies of 81.8% and 78.2% for morning and afternoon shifts increased to 92% and 86.5%, respectively, when five robots were deployed. Different scheduling policies did not affect efficiency when more than five robots were used, because there were always enough robots to serve pickers' requests immediately. Also, harvest efficiency plateaued when more than five robots were used, as a consequence of the time needed for a robot to travel to a picker.

Manual harvesting of fresh-market crops like strawberries is very labor-intensive. Apart from picking fruits, pickers spend significant amounts of time carrying full trays to a collection station at the edge of the field. Small teams of harvest-aid robots that help large picking crews by transporting empty and full trays can increase harvest efficiency by reducing pickers' non-productive walking times. However, robot sharing among the crew may introduce non-productive waiting delays between the time a tray becomes full and when a robot arrives to collect it. Reactive robot scheduling cannot eliminate mean waiting times because pickers must wait for a robot to travel the distance from the collection station to them. Predictive scheduling is better suited to this task, because if the time and location that a pickers' tray will fill are known to the scheduler in advance, a robot can start moving toward that location before the tray becomes full; hence, waiting times due to robot travel can be reduced or eliminated. In this paper, dynamic predictive scheduling was modeled for teams of robots carrying trays during manual harvesting. The times and locations of the tray-transport requests were assumed to be known exactly (deterministic predictions). Near-optimal scheduling was implemented to provide efficiency upper-bounds for any predictive scheduling algorithms that incorporate uncertainty in the predictive requests. Robot-aided harvesting was simulated using manual-harvest data collected from a commercial picking crew. Scheduling performance was studied as a function of the number of robots - for a given crew size - with robot speed as a parameter. Additionally, the effect of the earliness of the availability of the predictions on performance was studied. Experimental results showed that both reactive and predictive scheduling did not improve the mean nonproductive time significantly relative to manual harvesting, when only four robots were used. Actually, deploying fewer than four robots led to worse non-productive time. However, introducing five to eight robots decreased mean non-productive time drastically, and when ten or more robots were used, non-productive time was reduced by 64.6% (reactive scheduling) and up to 93.7% (predictive scheduling) with respect to all-manual non-productive time. The efficiency increases were 15% and 24%, respectively. It was also verified that reactive dispatching always performed worse than deterministic predictive scheduling. Also, when the robot-to-picker ratio was larger than approximately 1:3, the waiting time and efficiency plateaued, i.e., did not improve further, regardless of how early the prediction was available to the scheduler. The reason is that the mean waiting time is lower bounded by the sum of mean travel time and tray exchange time, which are both constant. Although the above results represent upper-bounds for performance - since predictions were perfect they indicate that traytransport robots acting as harvest aids can increase harvesting efficiency significantly when scheduled properly.