Advances in multi-robot technology have accelerated the development of smart agriculture, enabling tasks to be executed collaboratively with higher efficiency. In heterogeneous agricultural robots collaborative operation scheduling, fuzzy time window and matching constraints significantly increase the problem complexity. This paper proposes a multi-objective heterogeneous agricultural robot operation scheduling model with fuzzy service time window and matching constraints (MHROS_FT&M), aiming to optimize the total operation cost and service level. Given the NP-hard property of MHROS_FT&M, the hierarchical learning large neighborhood search algorithm (HLLNS) is developed. HLLNS incorporates the hierarchical reinforcement learning to enhance adaptability, a dynamic programming-based approach to improve service levels, and a sub-problem collaboration and mutation strategy to escape local optimum. By employing automated algorithm design technique to optimize 12 key parameters, the automated HLLNS (AHLLNS) is realized. In practical smart-farming scenarios, AHLLNS supports the joint scheduling of heterogeneous robots such as spraying drones, weeding robots, and seeding drones under uncertain service times, and explicitly balances operation cost against farmer satisfaction. The obtained schedules reduce unnecessary travel and resource consumption while keeping service times within acceptable ranges for farmers. Through automatic parameter tuning and the use of problem-specific operators, AHLLNS effectively addresses fuzzy time windows and matching constraints, achieving better performance across different problem scales. Experimental comparisons with Gurobi and state-of-the-art algorithms demonstrate AHLLNS superior computational efficiency and solution quality, validating its effectiveness for MHROS_FT&M.

In the realm of scheduling problems, metaheuristics have been widely embraced as superior solutions, appreciated for their ability to generate resolutions for non-deterministic polynomial-time hard (NP-hard) problems swiftly. This paper presents a novel parallel evolutionary algorithm (PEA), which marries metaheuristics and parallel computing to amplify computer performance utilization. Four operators and a restart strategy are incorporated into the proposed PEA to bolster both its global and local search capabilities. An accelerated calculation method for two operators is proposed. The algorithm also features an adaptive method that generates sub-threads and parameters based on computer performance, along with rotation for evaluating solutions. A random search sub-thread is established to update the solution. The algorithm is tested on the workshop automated guided vehicle (AGV) scheduling problem and compared against other optimization algorithms to ascertain its efficacy. The test results overwhelmingly highlight the superior performance of the proposed algorithm. Note to Practitioners—The paper introduces a novel parallel evolutionary algorithm (PEA) for scheduling problems, which combines metaheuristics and parallel computing to enhance computer performance utilization. The algorithm incorporates four operators and a restart strategy, along with an accelerated calculation method for two operators. It also includes an adaptive method to generate sub-threads and parameters based on computer performance, as well as rotation for evaluating solutions. A random search sub-thread is established to update the solution. The proposed algorithm is tested on the workshop automated guided vehicle (AGV) scheduling problem, producing superior results compared to other optimization algorithms. Its ability to swiftly generate resolutions for NP-hard problems can greatly benefit industries that rely on efficient scheduling, such as logistics and manufacturing. However, it is important to note that the algorithm has some limitations. Further research is needed to explore its application in different domains and evaluate its performance in more complex scheduling scenarios. Additionally, the algorithm’s scalability and adaptability need to be thoroughly examined to ensure its practicality in real-world settings.

In this article, we investigate the multiagent robust consensus problem under model uncertainties, where the uncertain matrices and initial values are bounded by prior intervals. Based on the positive system theory, the related upper and lower dynamic systems are constructed to guarantee that the state value remains within a specified range. Subsequently, in accordance with the Lyapunov stability principle, the observation and consensus errors converge to zero, that is, the real states are reconstructed and consensus is achieved. Both local and neighborhood protocols, which are utilized to realize robust consensus, are presented. Notably, the proposed methods increase the design freedom and eliminate the Metzler constraint on the error matrix by introducing two novel parametric matrices. Without loss of generality, the topology in this article is assumed to contain a directed spanning tree, which can be directly degenerated to the undirected graph. Finally, numerical simulations validating the theoretical results are described.

The sustainable scheduling of distributed manufacturing has received considerable attention from manufacturing researchers in developing sustainable manufacturing. The multi-objective sustainable distributed blocking flow shop scheduling problem with heterogeneous factories (HFMS-DBFSP) is studied in this paper. The model of the HFMS-DBFSP is proposed considering the three goals of total tardiness, total carbon emission, and negative social impact. A learning-based discrete Jaya algorithm (LDJaya) is presented to address the HFMS-DBFSP. The cooperative initialization method based on the characteristics of the HFMS-DBFSP is designed for population initialization. The self-learning operation selection strategy is introduced to guide the selection of operations, and local search operators are proposed to keep the population diverse. The carbon saving speed adjustment strategy is proposed to lower carbon emissions still further. The effectiveness of each of the strategies in the LDJaya is validated and benchmarked within the benchmark suite against the state-of-the-art algorithms. The simulation results of the experiment prove that the designed LDJaya is superior to other comparative algorithms in significance and efficiency in resolving the HFMS-DBFSP.

Robotic arms are key components in fruit-harvesting robots. In agricultural settings, conventional serial or parallel robotic arms often fall short in meeting the demands for a large workspace, rapid movement, enhanced capability of obstacle avoidance and affordability. This study proposes LingXtend, a novel hybrid six-degree-of-freedom (DoF) robotic arm that combines the advantages of parallel and serial mechanisms. Inspired by yoga, we designed two sliders capable of moving independently along a single rail, acting as two feet. These sliders are interconnected with linkages and a meshed-gear set, allowing the parallel mechanism to lower itself and perform a split to pass under obstacles. This unique feature allows the arm to avoid obstacles such as pipes, tables and beams typically found in greenhouses. Integrated with serially mounted joints, the patented hybrid arm is able to maintain the end’s pose even when it moves with a mobile platform, facilitating fruit picking with the optimal pose in dynamic conditions. Moreover, the hybrid arm’s workspace is substantially larger, being almost three times the volume of UR3 serial arms and fourteen times that of the ABB IRB parallel arms. Experiments show that the repeatability errors are 0.017 mm, 0.03 mm and 0.109 mm for the two sliders and the arm’s end, respectively, providing sufficient precision for agricultural robots.

With the advent of agriculture 4.0 era, the combination of agriculture and unmanned technology has promoted the development of intelligent agriculture. However, there are relatively few studies on the agricultural robot task allocation problem to optimize the cost and efficiency of smart farms. To make up this deficiency, this paper addresses a multi-picking-robot task allocation (MPRTA) problem with two objectives of minimizing the maximum completion time and minimizing the total travel length of all robots. An effective multi-objective discrete artificial bee colony (MODABC) algorithm is proposed to solve this problem. At first, a heuristic allocation method based on robot load balancing is designed to generate high-quality initial solutions. And then, a multi-objective self-adaptive strategy is proposed to enhance the exploitation and exploration of the algorithm. In addition, a multi-objective local search strategy for the non-dominated solutions is presented to help the population find better solutions. At last, extensive experiments based on different task sizes and robot scales of an intelligent orchard demonstrate the effectiveness and high performance of the proposed algorithm for solving the MPRTA problem.

In this article, we propose an efficient fault diagnosis framework to achieve accurate fault isolation. The core is to introduce the$\ell _{2,0}$-norm sparsity constrained optimization to reduce the variable redundancy and determine the variable number, which is different from the existing sparse variants. In order to illustrate the idea, this article takes principal component analysis (PCA) as an essential step. First, a sparsity-aware PCA is constructed by taking advantage of the$\ell _{2,0}$-norm constrained optimization. Afterward, a two-stage monitoring strategy is designed, including fault detection and fault isolation. Once the fault is detected, the sparsity level is then shrunk to achieve accurate fault isolation. Moreover, an alternating direction method of multipliers-based optimization algorithm is developed with detailed implementation. Finally, the detection improvement and accurate isolation performance are validated by two simulated examples, the Tennessee Eastman benchmark process, and a practical cylinder-piston process.

This paper deals with the distributed event-triggered formation control problem of networked nonholonomic mobile robots (NNMRs) in a leader-follower-based frame. The event-triggered mechanism (ETM) is first introduced for the design of the kinematic controller by a suitable auxiliary (or virtual) reference vector, and a unified integrated dynamic controller is then proposed in combination with backstepping technique and sliding mode approach. The designed event-triggered condition is derived based on the local communication among robots by the best use of nonholonomic property of NNMRs, which can fully guarantee to exclude the Zeno behavior before the desired formation configuration is achieved. Finally, the theoretical results are validated through simulation analysis, and then implemented on experimental platform for real-time physical NNMRs. Moreover, both simulation and experimental results demonstrate the key feature of the ETM integral formation scheme, it can effectively reduce communication resource usage and save energy while still providing comparable performance compared with the conventional periodic communication mechanism (PCM).

Generalized canonical correlation analysis (GCCA) that aims to deal with multi-view data has attracted extensive attention in signal processing. To improve the representation performance, this letter proposes a new sparsity constrained GCCA (SCGCCA). Technically, it integrates the$\ell _{2,0}$-norm constrained optimization into GCCA, which has not been investigated in the literature. Compared with the existing$\ell _{2,1}$-norm regularized GCCA, the proposed SCGCCA can not only exploit the similarity information belonging to the same features but also determine the number of extracted features. Although it is a nonconvex minimization problem, an efficient alternating minimization algorithm can be designed. Furthermore, a Newton hard thresholding pursuit technique is developed to accelerate the convergence tremendously. Empirical studies suggest both the effectiveness and efficiency of the proposed SCGCCA comparing with the existing GCCA and its variants. In particular, the speed can be increased by 150 times for the simulated dataset.

Circadian function and p53 network are interconnected on the molecular level, but the dynamics induced by the interaction between the circadian factor Per2 and the tumor suppressor p53 remains poorly understood. Here, we constructed an integrative model composed of a circadian clock module and a p53-Mdm2 feedback module to study the dynamics of p53-Per2 network in unstressed cells. As expected, the model can accurately predict the circadian rhythm, which is consistent with diverse experimental observations. In addition, using a combination of theoretical analysis and numerical simulation, the results demonstrated that p53 expression enhances the phase advance of circadian rhythm and reduces the robustness of circadian rhythm. Furthermore, the time delay required for the transcription and translation of Per2 protein induces oscillations by undergoing a supercritical Hopf bifurcation, and improves the robustness of circadian rhythm. In summary, this work shows that the p53-Per2 interaction and the time delay are two essential factors for circadian functions.

This article proposes an efficient nonlinear process monitoring method (DCCA-SCO) by integrating canonical correlation analysis (CCA), deep autoencoder neural networks (DAENNs), and sparsity-constrained optimization (SCO). Specifically, DAENNs are first used to learn a nonlinear function automatically, which characterizes intrinsic features of the original process data. Then, the CCA is performed in that low-dimensional representation space to extract the most correlated variables. In addition, the SCO is imposed to reduce the redundancy of the hidden representation. Unlike other deep CCA methods, the DCCA-SCO provides a new nonlinear method that is able to learn a nonlinear mapping with a sparse prior. The validity of the proposed DCCA-SCO is extensively demonstrated on the benchmark Tennessee Eastman (TE) process and the diesel generator process. In particular, compared with the classical CCA, the fault detection rate is increased by 8.00% for the fault IDV(11) in the TE process.

Although the dynamical behavior of the p53-Mdm2 loop has been extensively studied, the understanding of the mechanism underlying the regulation of this pathway still remains limited. Herein, we developed an integrated model with five basic components and three ubiquitous time delays for the p53-Mdm2 interaction in response to DNA damage following ionizing radiation (IR). We showed that a sufficient amount of activated ATM level can initiate the p53 oscillations with nearly the same amplitude over a wide range of the ATM level; a proper range of p53 level is also required for generating the oscillations, for too high or too low levels it would fail to generate the oscillations; and increased Mdm2 level leads to decreased amplitude of the p53 oscillation and reduced expression of the p53 activity. Moreover, we found that the negative feedback loop formed between p53 and nuclear Mdm2 plays a dominant role in determining the p53 dynamics, whereas when interaction strength of the negative feedback loop becomes weaker, the positive feedback loop formed between p53 and cytoplasmatic Mdm2 can induce different types of dynamics. Furthermore, we demonstrated that the total time delay required for protein production and nuclear translocation of Mdm2 can induce p53 oscillations even when the p53 level is at a certain stable high steady state or at a certain stable low steady state. In addition, the two important features of the oscillatory dynamics-amplitude and period-can be controlled by such time delay. These results are in agreement with multiple experimental observations and may enrich our understanding of the dynamics of the p53 network.

Parturient paresis(milk fever) is a common disease associated with the onset of parturition in dairy cows. The disease is considered due to a large increased demand for calcium. Several work has mathematically and biologically modelled this process. Based on the existing models on calcium dynamics in diary cows, an optimal impulse treatment is proposed in this paper. The treatment is executed at a fixed time interval and lasts a relatively very small time duration, which is termed as a "fixed time impulse" control. For the optimization, with a selected objective function, a series of equations for optimality are to be satisfied, including control equations, costate equations and state equations. Those impulsive differential equations form a two point boundary value problem and are difficult to solve. A numerical scheme, SNAC(Single Network Adaptive Critic), is then proposed. The algorithm key is to use one neural network to capture the optimal relation between the pre-impulse state and the after-impluse costate. After the neural network is trained and the relation is captured, the optimal impulse dosage of medicine can be provided when a parturient paresis is detected, and the cow's calcium level can be brought back to the normal status. Simulations are presented for illustrative purposes.

We investigate the optimization of linear impulse systems with the reinforcement learning based adaptive dynamic programming (ADP) method. For linear impulse systems, the optimal objective function is shown to be a quadric form of the pre-impulse states. The ADP method provides solutions that iteratively converge to the optimal objective function. If an initial guess of the pre-impulse objective function is selected as a quadratic form of the pre-impulse states, the objective function iteratively converges to the optimal one through ADP. Though direct use of the quadratic objective function of the states within the ADP method is theoretically possible, the numerical singularity problem may occur due to the matrix inversion therein when the system dimensionality increases. A neural network based ADP method can circumvent this problem. A neural network with polynomial activation functions is selected to approximate the pre-impulse objective function and trained iteratively using the ADP method to achieve optimal control. After a successful training, optimal impulse control can be derived. Simulations are presented for illustrative purposes.