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.

Polyculture farming, where multiple crop species are grown simultaneously, has potential to reduce pesticide and water usage while improving the utilization of soil nutrients. However, it is much harder to automate polyculture than monoculture. To facilitate research, we present AlphaGardenSim, a fast, first order, open-access polyculture farming simulator with single plant growth and irrigation models tuned using real world measurements. AlphaGardenSim can be used for policy learning as it simulates inter-plant dynamics, including light and water competition between plants in close proximity and approximates growth in a real greenhouse garden at 25,$000\times $the speed of natural growth. This paper extends earlier work with a new action space that includes planting, which dynamically finds new seed locations that increases resources utilization, and an adaptive sampling technique to reduce the number of actions taken at each timestep without affecting performance. We also evaluate other automation policies using a novel metric that combines plant diversity and canopy coverage. Code and supplementary material can be found athttps://github.com/BerkeleyAutomation/AlphaGarden.Note to Practitioners—Monoculture farming is often characterized by heavy agrichemical inputs, such as chemical fertilizers and pesticides, and increased vulnerability to disease and pestilence. This paper is motivated by the lack of long-term sustainability of industrial agriculture, and its implications for human food security. Although polyculture is a sustainable alternative to monoculture farming, it requires more human labor and is more challenging to automate. In this paper we propose a fast, first order simulator that simulates the growth of plants in a polyculture setting. Simulation experiments suggest that the simulator can be used to learn a planting, watering and pruning plan a robot can follow to produce maximal yield from a diverse set of plants with limited irrigation, however it has not yet been tested on a physical garden. In future research we will develop a fully automated controller that will operate planting, irrigation and pruning tools in a physical garden over multiple plant growth cycles.

Polyculture farming is a sustainable farming technique based on synergistic interactions between differing plant types that make them more resistant to diseases and pests and better able to retain water. Reduced uniformity can reduce use of pesticides, fertilizer, and water, but is more labor intensive and more challenging to automate. We describe a scaled physical testbed (1.5m×3.0m) that uses a high resolution camera and soil sensors to monitor polyculture plants to facilitate tuning of plant growth, companion effects, and irrigation parameters for a first-order garden simulator. We use this simulator to develop a novel seed placement algorithm that increases coverage and diversity, and a learned pruning policy. In simulation experiments, the seed placement algorithm yields 60% more coverage and 10% more diversity than random seed placement and the learned pruning policy runs 1000X faster than a procedural lookahead policy to achieve high leaf coverage and plant diversity on adversarial gardens that include plant species with diverse growth rates. These models and policies provide the groundwork for a fully-automated system under development. Code, datasets and supplementary material can be found at https://github.com/BerkeleyAutomation/AlphaGarden/.

We consider the problem of multirobot routing in vineyards, a task motivated by our ongoing project aiming at creating a corobotic system to implement precision irrigation on large-scale commercial vineyards. The problem is related to a combinatorial optimization problem on graphs called “team orienteering.” Team orienteering is known to be NP-hard, thus motivating the development of heuristic solutions that can scale to large problem instances. We propose three different parameter-free approaches informed by the domain we consider and compare them against a general purpose heuristic developed previously. In numerous benchmarks derived from data gathered in a commercial vineyard, we demonstrate that our solutions outperform the general purpose heuristic and are scalable, thus allowing us to solve instances with tens of thousands of vertices in the graphs. Note to Practitioners-Routing problems with budget and motion constraints are pervasive to many applications. In particular, the structural constraints considered in this problem are found not only in agricultural environments but also in warehouse logistics and other domains where goods are arranged along regular linear structures. This article proposes and analyzes algorithms that can be applied when multiple agents must be coordinated in these environments. In particular, by utilizing domain-specific knowledge, the solutions proposed in this article outperform general purpose approaches that poorly scale with the size of the environment. The algorithms we present also ensure that no collisions occur between robots-an aspect normally neglected in algorithms previously proposed to solve the team orienteering problem.

International audience

When robots navigate through vineyards to perform irrigation adjustments, an optimization problem emerges whereby robots are tasked with performing adjustments having the highest cumulative outcome within a given temporal budget due to limited battery charge. To this end, the robot needs to reach a set of spatially distributed sites, and the specific structure of the vineyard imposes various constraints on possible motions. In this paper we first demonstrate that this type of orienteering problem remains NP-hard even for the restricted class of graphs associated with precision irrigation. Then, we devise and analyze two greedy heuristics informed by the problem we consider. Finally, these algorithms are evaluated on settings associated with a commercial vineyard and we show that our methods favorably compare to solutions proposed in the past.

International audience

In this paper, a nonlinear model predictive tracking (NMPT) controller for mobile robots is presented. The basic idea is to use a motion model for the vehicle and compute in real-time an optimal M-step-ahead control sequence, which minimizes the total M+l step tracking error of the projected motion. In the presence of obstacles, the controller deviates from the reference trajectory by incorporating into the optimization obstacle-distance information from range sensors (e.g., laser scanner, ultrasound). Numerous simulations were performed and the NMPT consistently converged to the desired trajectories and followed them accurately, despite large initial errors and discontinuities in the desired velocities and orientations. The controller's performance depended strongly on parameters such as the optimization horizon M, and the cost-weights assigned to the various tracking errors. The optimization horizon regulates a trade-off between timely obstacle avoidance and tracking quality (large M) vs. consistently fast convergence (small M). The cost-weights affect tracking quality and also the shape of the path, by regulating trade-offs among position, orientation, and velocity errors. Overall, NMPT seems to offer a promising approach for advanced precision guidance applications, and deserves further investigation.

Randomized path planners have been successfully used to compute feasible paths for difficult planning problems. Such paths are typically computed without taking into account any optimality criteria and may contain many “jagged” segments because of the randomness involved in their generation. This paper presents a two-phase path planning algorithm, which uses a randomized planner to compute low-cost paths, and gradient descent to locally optimize these paths by minimizing a Hamiltonian function. The algorithm is tested on motion planning for a non-holonomic car-like robot. The results indicate that the two-phase approach is practical; however, gradient descent seems to be inefficient for the optimization of long paths.

In robotic assembly operations the robot comes in contact with the environment and some form of compliance is typically used to prevent excessive contact forces. These contact forces provide information about the contact geometry and can be used to guide the assembly operation. Thus, compliance can be thought of as a task-dependent mapping from sensed forces to corrective motions which bring the robot closer to its goal. In this work we describe a methodology for the automated synthesis and verification of this mapping. The possible erroneous configurations of the robot are computed via Monte-Carlo simulation of the task execution. The static contact force at each erroneous contact configuration is computed and a corrective motion is computed and mapped to the force. The validity of the mapping is also checked to ensure that the sensed forces will provide unambiguous information during the actual execution of the planned compliant motion. Simulation and experimental results are also presented.