Elsevier BV Acta Medica Okayama 0952-1976 150 2025 Surrogate-assisted motion planning and layout design of robotic cellular manufacturing systems 110530 EN Tomoya Kawabe Graduate School of Environmental, Life and Natural Science and Technology, Okayama University Tatsushi Nishi Graduate School of Environmental, Life and Natural Science and Technology, Okayama University Ziang Liu Graduate School of Environmental, Life and Natural Science and Technology, Okayama University Tomofumi Fujiwara Graduate School of Environmental, Life and Natural Science and Technology, Okayama University A surrogate-assisted multi-objective evolutionary algorithm is proposed for simultaneous optimization of robot motion planning and layout design in robotic cellular manufacturing systems. A sequence-pair is used to represent the layout of components in a robotic cell to avoid overlapping in the evolutionary computation. The robot motion planning with Rapidly exploring Random Trees Star (RRT*) is applied to compute the total operation time of a robot arm for each layout. Non-dominated Sorting Genetic Algorithm II (NSGA-II) is used to minimize the total required layout area and the operation time for a robot arm. The proposed surrogate model can estimate the robot’s operation time with 98% of accuracy without explicit computations of the motion planning algorithm. The experimental results with a physical 6 Degree of Freedom (DOF) manipulator show that the total computation time is approximately 1/400, significantly shorter than the conventional methods. No potential conflict of interest relevant to this article was reported.

MDPI Acta Medica Okayama 2076-3417 15 5 2025 Deep Reinforcement Learning for Dynamic Pricing and Ordering Policies in Perishable Inventory Management 2421 EN Yusuke Nomura Graduate School of Environmental, Life, Natural Science and Technology, Okayama University Ziang Liu Graduate School of Environmental, Life, Natural Science and Technology, Okayama University Tatsushi Nishi Graduate School of Environmental, Life, Natural Science and Technology, Okayama University Perishable goods have a limited shelf life, and inventory should be discarded once it exceeds its shelf life. Finding optimal inventory management policies is essential since inefficient policies can lead to increased waste and higher costs. While many previous studies assume the perishable inventory is processed following the First In, First Out rule, it does not reflect customer purchasing behavior. In practice, customers' preferences are influenced by the shelf life and price of products. This study optimizes inventory and pricing policies for a perishable inventory management problem considering age-dependent probabilistic demand. However, introducing dynamic pricing significantly increases the complexity of the problem. To tackle this challenge, we propose eliminating irrational actions in dynamic programming without sacrificing optimality. To solve this problem more efficiently, we also implement a deep reinforcement learning algorithm, proximal policy optimization, to solve this problem. The results show that dynamic programming with action reduction achieved an average of 63.1% reduction in computation time compared to vanilla dynamic programming. In most cases, proximal policy optimization achieved an optimality gap of less than 10%. Sensitivity analysis of the demand model revealed a negative correlation between customer sensitivity to shelf lives or prices and total profits. No potential conflict of interest relevant to this article was reported.

Taylor and Francis Acta Medica Okayama 0883-9514 38 1 2024 Surrogate-Assisted Multi-Objective Optimization for Simultaneous Three-Dimensional Packing and Motion Planning Problems Using the Sequence-Triple Representation 2398895 EN Ziang Liu Faculty of Environmental, Life, Natural Science and Technology, Okayama University Tomoya Kawabe Faculty of Environmental, Life, Natural Science and Technology, Okayama University Tatsushi Nishi Faculty of Environmental, Life, Natural Science and Technology, Okayama University Shun Ito Faculty of Environmental, Life, Natural Science and Technology, Okayama University Tomofumi Fujiwara Faculty of Environmental, Life, Natural Science and Technology, Okayama University Packing problems are classical optimization problems with wide-ranging applications. With the advancement of robotic manipulation, there are growing demands for the automation of packing tasks. However, the simultaneous optimization of packing and the robot's motion planning is challenging because these two decisions are interconnected, and no previous study has addressed this optimization problem. This paper presents a framework to simultaneously determine the robot's motion planning and packing decision to minimize the robot's processing time and the container's volume. This framework comprises three key components: solution encoding, surrogate modeling, and evolutionary computation. The sequence-triple representation encodes complex packing solutions by a sequence of integers. A surrogate model is trained to predict the processing time for a given packing solution to reduce the computational burden. Training data is generated by solving the motion planning problem for a set of packing solutions using the rapidly exploring random tree algorithm. The Non-Dominated Sorting Genetic Algorithm II searches for the Pareto solutions. Experimental evaluations are conducted using a 6-DOF robot manipulator. The experimental results suggest that implementing the surrogate model can reduce the computational time by 91.1%. The proposed surrogate-assisted optimization method can obtain significantly better solutions than the joint angular velocity-based estimation method. No potential conflict of interest relevant to this article was reported.

Springer Acta Medica Okayama 2199-4536 10 1 2023 Data-driven evolutionary computation for service constrained inventory optimization in multi-echelon supply chains 825 846 EN Ziang Liu Faculty of Environmental, Life, Natural Science and Technology, Okayama University Tatsushi Nishi Faculty of Environmental, Life, Natural Science and Technology, Okayama University Supply chain digital twin has emerged as a powerful tool in studying the behavior of an actual supply chain. However, most studies in the field of supply chain digital twin have only focused on what-if analysis that compares several different scenarios. This study proposes a data-driven evolutionary algorithm to efficiently solve the service constrained inventory optimization problem using historical data that generated by supply chain digital twins. The objective is to minimize the total costs while satisfying the required service level for a supply chain. The random forest algorithm is used to build surrogate models which can be used to estimate the total costs and service level in a supply chain. The surrogate models are optimized by an ensemble approach-based differential evolution algorithm which can adaptively use different search strategies to improve the performance during the computation process. A three-echelon supply chain digital twin on the geographic information system (GIS) map in real-time is used to examine the efficiency of the proposed method. The experimental results indicate that the data-driven evolutionary algorithm can reduce the total costs and maintain the required service level. The finding suggests that our proposed method can learn from the historical data and generate better inventory policies for a supply chain digital twin. No potential conflict of interest relevant to this article was reported.

MDPI Acta Medica Okayama 2076-3417 13 3 2023 Flexible Route Planning for Multiple Mobile Robots by Combining Q-Learning and Graph Search Algorithm 1879 EN Tomoya Kawabe Graduate School of Natural Science and Technology, Okayama University Tatsushi Nishi Graduate School of Natural Science and Technology, Okayama University Ziang Liu Graduate School of Natural Science and Technology, Okayama University The use of multiple mobile robots has grown significantly over the past few years in logistics, manufacturing and public services. Conflict-free route planning is one of the major research challenges for such mobile robots. Optimization methods such as graph search algorithms are used extensively to solve route planning problems. Those methods can assure the quality of solutions, however, they are not flexible to deal with unexpected situations. In this article, we propose a flexible route planning method that combines the reinforcement learning algorithm and a graph search algorithm for conflict-free route planning problems for multiple robots. In the proposed method, Q-learning, a reinforcement algorithm, is applied to avoid collisions using off-line learning with a limited state space to reduce the total learning time. Each vehicle independently finds the shortest route using the A* algorithm, and Q-learning is used to avoid collisions. The effectiveness of the proposed method is examined by comparing it with conventional methods in terms of computation time and the quality of solutions. Computational results show that for dynamic transportation problems, the proposed method can generate the solutions with approximately 10% of the computation time compared to the conventional Q-learning approach. We found that the required computation time is linearly increased with respect to the number of vehicles and nodes in the problems. No potential conflict of interest relevant to this article was reported.

MDPI Acta Medica Okayama 2076-3417 12 19 2022 Machine Learning and Inverse Optimization for Estimation of Weighting Factors in Multi-Objective Production Scheduling Problems 9472 EN Hidetoshi Togo Graduate School of Natural Science and Technology, Okayama University Kohei Asanuma Graduate School of Engineering Science, Osaka University Tatsushi Nishi Graduate School of Natural Science and Technology, Okayama University Ziang Liu Graduate School of Natural Science and Technology, Okayama University In recent years, scheduling optimization has been utilized in production systems. To construct a suitable mathematical model of a production scheduling problem, modeling techniques that can automatically select an appropriate objective function from historical data are necessary. This paper presents two methods to estimate weighting factors of the objective function in the scheduling problem from historical data, given the information of operation time and setup costs. We propose a machine learning-based method, and an inverse optimization-based method using the input/output data of the scheduling problems when the weighting factors of the objective function are unknown. These two methods are applied to a multi-objective parallel machine scheduling problem and a real-world chemical batch plant scheduling problem. The results of the estimation accuracy evaluation show that the proposed methods for estimating the weighting factors of the objective function are effective. No potential conflict of interest relevant to this article was reported.

MDPI Acta Medica Okayama 1996-1073 15 6 2022 Energy-Efficient Robot Configuration and Motion Planning Using Genetic Algorithm and Particle Swarm Optimization 2074 EN Kazuki Nonoyama Graduate School of Natural Science and Technology, Okayama University Ziang Liu Graduate School of Natural Science and Technology, Okayama University Tomofumi Fujiwara Graduate School of Natural Science and Technology, Okayama University Md Moktadir Alam Graduate School of Natural Science and Technology, Okayama University Tatsushi Nishi Graduate School of Natural Science and Technology, Okayama University The implementation of Industry 5.0 necessitates a decrease in the energy consumption of industrial robots. This research investigates energy optimization for optimal motion planning for a dual-arm industrial robot. The objective function for the energy minimization problem is stated based on the execution time and total energy consumption of the robot arm configurations in its workspace for pick-and-place operation. Firstly, the PID controller is being used to achieve the optimal parameters. The parameters of PID are then fine-tuned using metaheuristic algorithms such as Genetic Algorithms and Particle Swarm Optimization methods to create a more precise robot motion trajectory, resulting in an energy-efficient robot configuration. The results for different robot configurations were compared with both motion planning algorithms, which shows better compatibility in terms of both execution time and energy efficiency. The feasibility of the algorithms is demonstrated by conducting experiments on a dual-arm robot, named as duAro. In terms of energy efficiency, the results show that dual-arm motions can save more energy than single-arm motions for an industrial robot. Furthermore, combining the robot configuration problem with metaheuristic approaches saves energy consumption and robot execution time when compared to motion planning with PID controllers alone. No potential conflict of interest relevant to this article was reported.

MDPI Acta Medica Okayama 2076-3417 11 1 2021 Multi-Period Maximal Covering Location Problem with Capacitated Facilities and Modules for Natural Disaster Relief Services 397 EN Roghayyeh Alizadeh Division of Mathematical Science for Social Systems, Department of Systems Innovation, Graduate School of Engineering Science, Osaka University Tatsushi Nishi Graduate School of Natural Sciences, Department of Industrial Innovation Engineering, Okayama University Jafar Bagherinejad Department of Industrial Engineering, Faculty of Engineering, Alzahra University Mahdi Bashiri School of Strategy and Leadership, Faculty of Business and Law, Coventry University The paper aims to study a multi-period maximal covering location problem with the configuration of different types of facilities, as an extension of the classical maximal covering location problem (MCLP). The proposed model can have applications such as locating disaster relief facilities, hospitals, and chain supermarkets. The facilities are supposed to be comprised of various units, called the modules. The modules have different sizes and can transfer between facilities during the planning horizon according to demand variation. Both the facilities and modules are capacitated as a real-life fact. To solve the problem, two upper bounds-(LR1) and (LR2)-and Lagrangian decomposition (LD) are developed. Two lower bounds are computed from feasible solutions obtained from (LR1), (LR2), and (LD) and a novel heuristic algorithm. The results demonstrate that the LD method combined with the lower bound obtained from the developed heuristic method (LD-HLB) shows better performance and is preferred to solve both small- and large-scale problems in terms of bound tightness and efficiency especially for solving large-scale problems. The upper bounds and lower bounds generated by the solution procedures can be used as the profit approximation by the managerial executives in their decision-making process. No potential conflict of interest relevant to this article was reported.

MDPI Acta Medica Okayama 2076-3417 10 20 2020 Hybrid Set Covering and Dynamic Modular Covering Location Problem: Application to an Emergency Humanitarian Logistics Problem 7110 EN Roghayyeh Alizadeh Division of Mathematical Science for Social Systems, Department of Systems Innovation, Graduate School of Engineering Science, Osaka University Tatsushi Nishi Graduate School of Natural Sciences, Department of Industrial Innovation Engineering, Okayama University This paper presents an extension of the covering location problem as a hybrid covering model that utilizes the set covering and maximal covering location problems. The developed model is a multi-period model that considers strategic and tactical planning decisions. Hybrid covering location problem (HCLP) determines the location of the capacitated facilities by using dynamic set covering location problem as strategic decisions and assigns the constructive units of facilities and allocates the demand points by using dynamic modular capacitated maximal covering location problem as tactical decisions. One of the applications of the proposed model is locating first aid centers in humanitarian logistic services that have been addressed by studying a threat case study in Japan. In addition to validating the developed model, it has been compared to other possible combined problems, and several randomly generated examples have been solved. The results of the case study and model validation tests approve that the main hybrid developed model (HCLP) is capable of providing better coverage percentage compared to conventional covering models and other hybrid variants. No potential conflict of interest relevant to this article was reported.