Robotic Cell Scheduling Research Articles

Deep Reinforcement Learning With a Look-Ahead Search for Robotic Cell Scheduling

Deep Reinforcement Learning With a Look-Ahead Search for Robotic Cell Scheduling

Bi-objective speed-scaling robotic cell scheduling with peak power consumption constraint

This article studies the speed-scaling robotic cell scheduling problem with constrained peak power consumption. The objective is to minimize cycle time and peak power consumption simultaneously. First, we formulate a bi-objective mixed integer programming model for the problem and propose a strategy to preprocess overlapping time windows. Then, we analyze the structural properties of the proposed model and develop an iterative $ \varepsilon $-constraint method to generate its complete Pareto front. Numerical experiments demonstrate that the proposed method effectively solves the robotic cell scheduling problem and that appropriate scheduling of speed-scaling machines can make a trade-off between productivity and power consumption.

A Bender’s Algorithm of Decomposition Used for the Parallel Machine Problem of Robotic Cell

The present research addresses the single transportation robot used to alleviate problems of robotic cell scheduling of the machines. For the purpose of minimizing the make-span, a model of mixed-integer linear programming (MILP) has been suggested. Since the inefficiency exists in NP-hard, a decomposition algorithm posed by Bender was utilized to alleviate the problem in real life situations. The proposed algorithm can be regarded as an efficient attempt to apply optimality Bender’s cuts regarding the problem of parallel machine robotic cell scheduling in order to reach precise resolutions for medium and big sized examples. The numerical analyses have demonstrated the efficiency of the proposed solving approach.

Scheduling of Dual-Gripper Robotic Cells With Reinforcement Learning

A dual-gripper robotic cell consists of multiple processing machines and one material handling robot, which can perform an unloading or a loading task one at a time but can hold two parts at the same time. We address a scheduling problem of the robotic cell that determines a robot task sequence when two part types are processed in a different set of machines and all machines have variable processing times within a given interval. The objective is to minimize the makespan. This study proposes a learning-based method, i.e., a reinforcement learning (RL) approach, for the first time, to address a dual-gripper robotic cell scheduling problem. The problem is modeled with a Petri net, a graphical and mathematical modeling tool, which is used as an environment in RL. The states, actions, and rewards are defined by using flow shop scheduling properties, features from a Petri net, and knowledge from previous studies of scheduling robotized tools. Then, the RL approach is compared to the first-in-first-out (FIFO) rule, which is generally used in practice, a swap sequence, which is widely used for cyclic scheduling of dual-gripper robotic cells, and a lower bound. The extensive experiments show that the proposed method performs better than FIFO and the swap sequence; moreover, the gap between the makespan of the proposed method and the lower bound is not large. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —We address a scheduling problem of dual-gripper robotic cells with two-part types when all machines have processing time variations. We propose an RL approach to obtain an efficient robot task sequence in order to minimize makespan. The proposed method is performed offline, and a robot task sequence is then obtained instantaneously. The proposed method performs better than the FIFO rule used in practice and the swap sequence used for cyclic scheduling of robotic cells. It can be easily extended for scheduling other configurations of robotic cells.

Fuzzy Gilmore and Gomory algorithm: Application in robotic flow shops with the effects of job-dependent transportation and set-ups

This paper addresses the scheduling of robotic cells with job-dependent transportation and set-up effects with fuzzy methodology. Since transportation and set-up times are a large portion of the production time in a flexible manufacturing cell, ignoring these parameters may cause significant errors in determining the optimal makespan. Furthermore, determining the exact values of these time parameters is a challenging task. To overcome this problem, we represent these parameters using fuzzy L-R numbers. Using the capability of fuzzy numbers to represent approximate values, we can represent these parameters without losing valuable information. For generating the optimal part sequencing in the cells, the Gilmore and Gomory algorithm is modified, and instead, a fuzzy Gilmore and Gomory algorithm is developed. We compare the results of the proposed fuzzy method with those of crisp ones. The results indicate the superiority of the proposed algorithm in terms of robustness, flexibility, and reduction of makespan.

Multiobjective Differential Evolution Algorithm for Solving Robotic Cell Scheduling Problem With Batch-Processing Machines

Robotic cell scheduling problem with batch-processing machines (RCSP-BMs) needs to determine the processing sequence and the transferring sequence simultaneously. The buffer size before and after the batch-processing machines has a big influence on the scheduling solution. A big amount of energy is always consumed by batch-processing machines. Hybrid flow shop scheduling has been proven NP-hard, and the features of the batch-processing machines in a flow shop make the hybrid flow shop scheduling more difficult. This study proposes a multiobjective differential evolution (DE) algorithm to address these issues. First, a mathematical optimization model is formulated for the RCSP-BMs to minimize makespan and energy consumption of the batch-processing machines. Second, the multiobjective DE algorithm (MODE) is developed. A green scheduling algorithm is designed to decode the individuals to balance the makespan and energy consumption. A local search method is also presented to help the searching escape from the local optimum. Finally, experiments are carried out, and the results show that the MODE can solve the robotic cell scheduling problem with batch-processing machines effectively and efficiently. Note to Practitioners-This study focuses on the robotic cell scheduling problem with batch-processing machines (RCSP-BMs) and discusses the influence of the buffer sizes and different batching methods on scheduling. In this study, we propose a green scheduling algorithm and a multiobjective differential evolution algorithm to optimize the makespan and the energy consumption of the batch-processing machines simultaneously. In future research, we will address more complicated situations, such as many-objective optimization and many-robot scheduling.

Energy conscious scheduling of a material handling robot in a manufacturing cell

In cyclic scheduling of material handling robots in manufacturing cells, a common approach is to minimize the cycle time objective, which is a measure of the throughput of the cell. In a typical robot move cycle, robot move times constitute a significant portion of the cycle time. During handling operations, robots consume significant amount of energy, which is determined by their speed, load and the distance they travel. In this paper, we propose considering robot speed decisions along with robot move sequencing decisions in a robotic cell scheduling problem. We study the trade-off between the cycle time and the energy consumption of a robot in a robotic cell which produces identical parts. In this cell, the robot loads and unloads the machines. Each machine performs a different operation on a part and the robot moves linearly along a track. We provide models to find efficient solutions for cycle time and robot energy consumption objectives in an m-machine robotic cell. In a case study for two machine robotic cell, we show that robot speed control can lead to significant savings in energy consumption.

Bacterial foraging optimization algorithm in robotic cells with sequence-dependent setup times

In this paper, we propose an improved discrete bacterial foraging algorithm to determine the optimal sequence of parts and robot moves in order to minimize the cycle time for the 2-machine robotic cell scheduling problem with sequence-dependent setup times. We present a method to convert the solutions from continuous to discrete form. In addition, two neighborhood search techniques are employed to updating the positions of each bacterium during chemotaxis and elimination–dispersal operations in order to accelerate the search procedure and to improve the solution. Moreover, a multi-objective optimization algorithm based on NSGA-II combined with the response surface methodology and the desirability technique is applied to tune the parameters as well as to enhance the convergence speed of the proposed algorithm. Finally, a design of experiment based on central composite design is used to determine the optimal settings of the operating parameters of the proposed algorithm. The results of the computational experimentation with a large number of randomly generated test problems demonstrate that the proposed method is relatively more effective and efficient than the state-of-the-art algorithms in minimizing the cycle time in the robotic cell scheduling.

An effective chemical reaction optimization for cyclic multi-type parts robotic cell scheduling problem with blocking

An effective chemical reaction optimization for cyclic multi-type parts robotic cell scheduling problem with blocking

Maintenance, shutdown and production scheduling in semiconductor robotic cells

Our approach is the first to study simultaneous scheduling of preventive maintenance, shutdowns and production for robotic cells in semiconductor manufacturing. It hereby exploits the frequent periods of overcapacity in semiconductor manufacturing to reduce wear and tear. In contrast to existing approaches, our scheduling approach is able to deal with different preventive-maintenance types. We borrow the Resource Task Network representation from the process-industry domain to represent our problem and facilitate its formulation as a mathematical model. In addition, we develop efficiency-improving constraints based on the characteristics of the preventive-maintenance activities. In numerical tests based on industry data, we show that the model generates high-quality schedules even without applying the inequalities, although the optimality gap is reduced only when including inequalities. We furthermore assess the trade-off between shutdowns and batch lead times. We compare our model’s schedule quality to (i) the simple industry practice of shutting down chambers permanently to reduce wear and tear and (ii) an approach that schedules maintenance and production sequentially. The numerical tests yield the following managerial insights. First, integrating maintenance and production scheduling has substantial advantages. Second, the practice of shutting equipment down permanently diminishes scheduling flexibility and solution quality. Third, shutdowns scheduling must also consider the impact on batch waiting times.

Trade-off between process scheduling and production cost in cyclic flexible robotic cells

In this study, a bi-objective scheduling problem of a flexible robotic cell is considered aiming to a trade-off between cell’s processes scheduling and the production cost. At the cell, machines are identical and parallel and in line. There is an input buffer for the raw materials and an output buffer for the products. A robot is in charge of loading and unloading of the items from the input buffer to machines and from machines to the out put buffer. The system is cyclic means repeats the same processes in every cycle. It is assumed that each machine processes one part in each cycle. A bi-objective mathematical model is presented to solve the problem, and as an alternative, an NSGAII is developed for large-sized problems. Several numerical examples are solved for examining the proposed mathematical model and NSGAII method.

A review of recent theoretical development in scheduling dual-gripper robotic cells

A robotic cell is a set of machines or processing centres served by a robot or a set of robots. Robotic cells can be classified by certain physical and operating characteristics such as robot type (single- or dual-gripper), robot travel-time (constant, additive or Euclidean) and types of parts processed (no-wait, interval processing time or free-pickup). Robotic cells are used in automated manufacturing systems where jobs or parts are produced in a typical flow shop type environment. A significant research effort has been directed towards analysing the problem of robot move sequencing in robotic cells served by single- or dual-gripper robot. In this review paper, we examine the recent theoretical developments on the analysis of throughput optimisation in robotic cells served by a dual-gripper robot. We focus on the problem of scheduling operations in dual-gripper robotic cells that produce identical parts. The objective is to find a cyclic sequence of robot moves that minimises the long-run average time to produce a part or, equivalently, maximises the throughput. The goals of this review paper are to: (i) provide a discussion of existing structural analysis, algorithmic and complexity results for robotic cells under conditions that are common in practice and (ii) present a set of open problems and future research directions. In addition to reporting recent results for dual-gripper robotic cell scheduling problems, we provide insight into a class of cyclic sequences that are not considered in practice but can improve throughput.

Scheduling method of robotic cells with machine–robot process and time window constraints

Robotic cells are widely used in the fields of incorporate automation and repetitive processing. Throughput analysis and scheduling of robotic cells with machine process have been well studied, while research work on robotic cells with machine–robot process in which robots concurrently perform collaborated tasks in addition to part transportation is still at an early stage. After defining the concepts of internal and external time window constraints, we propose a robotic cell scheduling problem with machine process and machine–robot process simultaneously, when processing time window is an essential constraint. According to the constraints in real engineering practice, a mathematic model of single-gripper robotic cells is established to minimize the average manufacturing cycle time. A shifting bottleneck searching algorithm is proposed based on the basis of analyses. In addition, a lower bound for the average manufacturing cycle time is established. Finally, through extensive simulation experiments, the numerical and experimental results demonstrate that the shifting bottleneck searching provides optimal or near optimal solutions.

Cyclic job shop robotic cell scheduling problem: Ant colony optimization

This paper deals with the cyclic job shop robotic cell scheduling problem with multiple robots. All the jobs are processed in order of their operations on multiple machines with standard processing times and the single gripper robots perform the transportation operations of jobs between the machines. Due to the special characteristics of the considered problem and NP-hard computational complexity, a metaheuristic algorithm based on ant colony optimization has been proposed. The proposed algorithm simultaneously determines the optimal height of jobs in the cyclic schedule, the robot assignments for transportation operations, and the optimal sequencing of the robots moves, which in return maximize the throughput rate. The efficiency of the proposed model is examined by a computational study on a set of randomly generated problem instances.

Increasing Throughput for a Class of Two-Machine Robotic Cells Served by a Multifunction Robot

The multifunction robotic cell scheduling problem has been recently studied in the literature. The main assumption in the pertaining literature is that a multifunction robot performs an operation on the part during any loaded move between two adjacent processing stages. For a two-machine cell, these stages are the input hopper, the first machine, the second machine and the output hopper. Consequently, the multifunction robot performs three operations with fixed processing times. In contrast, we assume a class of two-machine cells where none of the processing times of three operations are fixed. However, their summation is fixed and equivalent to the processing time of the unique operation. The processing mode of the unique operation performed by the multifunction robot is “stop resume.” Thus, regardless of the gap interrupts during operations by two machines, the robot continues performing the unique operation of the part when it is reloaded to the robot without any loss of time. The focus lies on $n$ -unit cycles due to their popularity. It is proven one-unit cycles have better performance for the problem under study. The cycle time of one-unit cycles are obtained and optimality conditions are determined for different pickup criteria: free, interval, and no-wait.

A framework for stochastic scheduling of two-machine robotic rework cells with in-process inspection system

This study is focused on the domain of a two-machine robotic cell scheduling problem for three various kinds of pickup scenarios: free, interval, and no-wait pickup scenarios. Particularly, we propose the first analytical method for minimizing the partial cycle time of such a cell with a PC-based automatic inspection system to make the problem more realistic. It is assumed that parts must be inspected in one of the production machines, and this may result in a rework process. The stochastic nature of the rework process prevents us from applying existing deterministic solution methods for the scheduling problem. This study aims to develop a framework for an in-line inspection of identical parts using multiple contact/non-contact sensors. Initially, we convert a multiple-sensor inspection system into a single-sensor inspection system. Then, the expected sequence times of two different cycles are derived based on a geometric distribution, and finally the maximum expected throughput is pursued for each individual case with free pickup scenario. Results are also extended for the interval and no-wait pick up scenarios as two well-solved classes of the scheduling problem. The waiting time of the part at each machine after finishing its operation is bounded within a fixed time interval in cells with interval pickup scenario, whereas the part is processed from the input conveyor to the output conveyor without any interruption on machines in cells with no-wait pickup scenario. We show a simple approach for solving these two scenarios of the problem which are common in practice.

Scheduling of two-machine robotic rework cells: In-process, post-process and in-line inspection scenarios

This study focuses on the domain of a two-machine robotic cell scheduling problem under three inspection scenarios. We propose the first analytical method for minimizing the partial cycle time of cells with in-process and post-process inspection scenarios, and then we convert this cell into a multi-function robotic cell with in-line inspection scenario. For the first scenario, parts are inspected in one of the production machines using multiple sensors, while the inspection process is performed by an independent inspection machine for the second scenario. Alternatively, the inspection can be performed by a multi-function robot for the third scenario. A distinguishing characteristic of this robot is that it can perform inspection of the part in transit. However, the robot cannot complete the part transition and load it on the next destination machine if it identifies a fault in the part. The stochastic nature of the process prevents us from applying existing deterministic solution methods for corresponding scheduling problems. In the first stage, we present a heuristic method that converts a multiple-sensor inspection system into a single-sensor inspection system. The expected cycle times of two different cycles are derived based on a geometric distribution, and then the maximum expected throughput is pursued for in-process and post-process inspection sensors, respectively. In the second stage, we develop the inspection system into an in-line inspection system using a multi-function robot. Finally, we determine if it is technically feasible and profitable to replace the in-process (or post-process) inspection scenario with the in-line inspection scenario.

Bacteria Foraging Optimization Algorithm for Robotic Cell Scheduling Problem

The present study deals with the application of BFO for solving robotic cell problem. One of the major disadvantages of Passino invented BFO is its applicability constrains for solving problems except those contain continuous domain. Thus to make BFO applicable in robotic cell problem, Pairwiseinterchange mutation is chosen for tumbling and swimming operation during chemotaxis.While cyclic-shift neighbourhood mutation is used for random movement duringElimination-Dispersal. The example related to the two-machine robotic cell scheduling problem with sequence-dependent setup times (2RCSDST) was used to demonstrate the performance of the proposed discrete bacteria foraging algorithm. Large part sized problems varying from 200 to 500 part size was considered during this study. The computational results thus obtained were compared with two other existing optimization techniques and found BFO as the better performer to solve such large sized problems.

Robot move sequence determining and multiple part-type scheduling in hybrid flexible flow shop robotic cells

We focus on the scheduling problem arising in hybrid flexible flow shops which repeatedly produce a set of multiple part-types and where the transportation of the parts between the machines is performed by a robot. The cycle time of the cell is affected by the robot move sequence, part/machine assignments and part sequences. In a hybrid flexible flow shop in which there exist one machine in the first and two machines in the second stage, the problem of determining the best cycle time is modeled as a traveling salesman problem. In order to provide a solution methodology for realistic problem instances, a Simulated Annealing based heuristic is constructed and the problem is solved using two different neighborhood structures. The results are also compared against an effective proposed lower bound value.

Multi-objective optimisation of dynamic scheduling in robotic flexible assembly cells via fuzzy-based Taguchi approach

This paper presents Taguchi method coupled with fuzzy logic for dealing with multi-objective optimisation problems for dynamic scheduling in robotic flexible assembly cells (RFACs). This is the first study to address these particular problems. In this study, Taguchi optimisation method has been applied to reduce the number of experiments required for scheduling RFACs. The experiments are implemented with four different scheduling factors, namely sequencing rule, dispatching rule, cell utilisation and due date tightness. These factors are difficult to optimise considering the objectives of multiple functions instead of a single objective. Therefore, a multiple performance characteristics index (MPCI) based fuzzy logic approach has been developed to derive the optimal solution. The predicted results of MPCIs have been verified via a confirmation test. Results of the confirmation test show significant improvement in MPCI using the optimal levels of the scheduling factors.