Pub Date : 2020-08-01DOI: 10.1109/CASE48305.2020.9216782
Sayyed Jaffar Ali Raza, Apan Dastider, Mingjie Lin
In this paper, a reinforcement learning method is presented to generate earthworm-like gaits for a hyperredundant earthworm-like manipulator robot. Partially inspired by human brain’s learning mechanism, the proposed learning framework builds its preliminary belief by first starting with adapting rudimentary gaits governed by a generic kinematic knowledge of undulatory, sidewinding and circular patterns. The preliminary belief is then represented as a prior ensemble to learn new gaits by leveraging apriori knowledge and learning a policy by inferring posterior over prior distribution. While the fundamental idea of incorporating Bayesian learning with reinforcement learning is not new, this paper extends Bayesian actor-critic approach by introducing augmented prior-based directed bias in policy search, aiding in faster parameter learning and reduced sampling requirements. We show results on an in-house built 10-DoF earthworm-like robot that exhibits adaptive development, qualitatively learning different locomotion modes, while given with only rudimentary generic gait behaviors. The results are compared against deterministic policy gradient method (DDPG) for continuous control as the baseline. We show that our proposed method can characterize effective performance over DDPG, and it also achieves faster kinematic indexes in various gaits.
{"title":"Developmentally Synthesizing Earthworm-Like Locomotion Gaits with Bayesian-Augmented Deep Deterministic Policy Gradients (DDPG)","authors":"Sayyed Jaffar Ali Raza, Apan Dastider, Mingjie Lin","doi":"10.1109/CASE48305.2020.9216782","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9216782","url":null,"abstract":"In this paper, a reinforcement learning method is presented to generate earthworm-like gaits for a hyperredundant earthworm-like manipulator robot. Partially inspired by human brain’s learning mechanism, the proposed learning framework builds its preliminary belief by first starting with adapting rudimentary gaits governed by a generic kinematic knowledge of undulatory, sidewinding and circular patterns. The preliminary belief is then represented as a prior ensemble to learn new gaits by leveraging apriori knowledge and learning a policy by inferring posterior over prior distribution. While the fundamental idea of incorporating Bayesian learning with reinforcement learning is not new, this paper extends Bayesian actor-critic approach by introducing augmented prior-based directed bias in policy search, aiding in faster parameter learning and reduced sampling requirements. We show results on an in-house built 10-DoF earthworm-like robot that exhibits adaptive development, qualitatively learning different locomotion modes, while given with only rudimentary generic gait behaviors. The results are compared against deterministic policy gradient method (DDPG) for continuous control as the baseline. We show that our proposed method can characterize effective performance over DDPG, and it also achieves faster kinematic indexes in various gaits.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132374107","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-08-01DOI: 10.1109/CASE48305.2020.9216952
Jingyi Song, A. Tanwani, Jeffrey Ichnowski, Michael Danielczuk, Kate Sanders, Jackson Chui, J. A. Ojea, Ken Goldberg
Robot grasping for automation must be robust to the inherent uncertainty in perception, control, and physical properties such as friction. Computing robust grasp points on a given object is even more challenging when there are constraints due to a task intended to be performed with the object, for example in assembly, packing, and/or tool use. To compute grasps that robustly achieve task requirements, we designed an intuitive user interface that takes an object mesh as input and displays it, allowing non-specialists to indicate “stay-out” zones by painting facets of the mesh and to indicate desired forces and torques by drawing vectors. The interface then sends this specification to our server which computes resulting grasps and send them back to the client where the resulting parallel-jaw grasp axes are displayed color-coded by robustness. We implemented this interface in the cloud-based “Dex-Net as a Service-Task (DNaaS-Task)” system that runs on any browser and reports examples. The system is available at: https://dex-net.app
{"title":"Robust Task-Based Grasping as a Service","authors":"Jingyi Song, A. Tanwani, Jeffrey Ichnowski, Michael Danielczuk, Kate Sanders, Jackson Chui, J. A. Ojea, Ken Goldberg","doi":"10.1109/CASE48305.2020.9216952","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9216952","url":null,"abstract":"Robot grasping for automation must be robust to the inherent uncertainty in perception, control, and physical properties such as friction. Computing robust grasp points on a given object is even more challenging when there are constraints due to a task intended to be performed with the object, for example in assembly, packing, and/or tool use. To compute grasps that robustly achieve task requirements, we designed an intuitive user interface that takes an object mesh as input and displays it, allowing non-specialists to indicate “stay-out” zones by painting facets of the mesh and to indicate desired forces and torques by drawing vectors. The interface then sends this specification to our server which computes resulting grasps and send them back to the client where the resulting parallel-jaw grasp axes are displayed color-coded by robustness. We implemented this interface in the cloud-based “Dex-Net as a Service-Task (DNaaS-Task)” system that runs on any browser and reports examples. The system is available at: https://dex-net.app","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130402027","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-08-01DOI: 10.1109/CASE48305.2020.9216774
Adolfo Perrusquía, Wen Yu, Xiaoou Li
Robot control in task-space1 needs the inverse kinematics and Jacobian matrix. They are not available for redundant robots, because there are so many degrees-of-freedom (DOF). Intelligent learning methods, such as neural networks (NN) and reinforcement learning (RL) can learn them. However, NN needs big data and RL is not suitable for multilink robots as the redundant robots. In this paper, we propose a full cooperative multi-agent reinforcement learning (MARL) to solve the above problems. Each joint of the robot is regarded as one agent. Although the dimension of the learning space is very large, the full cooperative MARL uses the kinematic learning and avoids the function approximators in large learning space. The experimental results show that our MARL is much more better compared with the classic methods such as, Jacobian-based methods and neural networks.1Task-space (or Cartesian space) is defined by the position and orientation of the end effector of a robot. Joint-space is defined by angular displacements of each joint of a robot.
{"title":"Redundant Robot Control Using Multi Agent Reinforcement Learning","authors":"Adolfo Perrusquía, Wen Yu, Xiaoou Li","doi":"10.1109/CASE48305.2020.9216774","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9216774","url":null,"abstract":"Robot control in task-space1 needs the inverse kinematics and Jacobian matrix. They are not available for redundant robots, because there are so many degrees-of-freedom (DOF). Intelligent learning methods, such as neural networks (NN) and reinforcement learning (RL) can learn them. However, NN needs big data and RL is not suitable for multilink robots as the redundant robots. In this paper, we propose a full cooperative multi-agent reinforcement learning (MARL) to solve the above problems. Each joint of the robot is regarded as one agent. Although the dimension of the learning space is very large, the full cooperative MARL uses the kinematic learning and avoids the function approximators in large learning space. The experimental results show that our MARL is much more better compared with the classic methods such as, Jacobian-based methods and neural networks.1Task-space (or Cartesian space) is defined by the position and orientation of the end effector of a robot. Joint-space is defined by angular displacements of each joint of a robot.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131737598","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-08-01DOI: 10.1109/CASE48305.2020.9216895
Biao Hu, Hao Chen, Zhengcai Cao, Chengran Lin
This work presents a self-adaptive cuckoo search algorithm with a new encoding mechanism to minimize the energy consumption in a heterogeneous distributed embedded system that runs tasks with arbitrary precedence constraints. We use the heterogeneous earliest-finish-time rule to construct a relatively high-quality initial solution. For the first time, a parameter feedback control scheme based on Monte-Carlo policy evaluation is used to balance the global and local search, in which way its search ability is greatly enhanced. In the end, the proposed self-adaptive cuckoo search approach is validated with two benchmarks and extensively randomly generated cases, and the experimental results demonstrate that our proposed approach have better performance than its counterparts.
{"title":"A Self-Adaptive Cuckoo Search Algorithm for Energy Consumption Minimization Problem with Deadline Constraint","authors":"Biao Hu, Hao Chen, Zhengcai Cao, Chengran Lin","doi":"10.1109/CASE48305.2020.9216895","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9216895","url":null,"abstract":"This work presents a self-adaptive cuckoo search algorithm with a new encoding mechanism to minimize the energy consumption in a heterogeneous distributed embedded system that runs tasks with arbitrary precedence constraints. We use the heterogeneous earliest-finish-time rule to construct a relatively high-quality initial solution. For the first time, a parameter feedback control scheme based on Monte-Carlo policy evaluation is used to balance the global and local search, in which way its search ability is greatly enhanced. In the end, the proposed self-adaptive cuckoo search approach is validated with two benchmarks and extensively randomly generated cases, and the experimental results demonstrate that our proposed approach have better performance than its counterparts.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"163 8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129282646","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-08-01DOI: 10.1109/CASE48305.2020.9216886
Y. Kim, T. Park
The Compact Camera Module (CCM) is a device used for various compact electronic devices such as notebooks, smartphones, etc. Various defects occur in the manufacturing process, such as scratches, stamps, and mura. Most notably, mura defect detection is the most challenging issue because of how normal it appears. With this, various methods based on deep learning have been developed to detect mura defects. However, previous research assumes that there is a substantial amount of training data. Therefore, classification accuracy decreases in an environment wherein it is difficult to obtain a sample of an actual defect. This study proposes a metric learning-based mura defect detection method with higher classification accuracy than the previous semantic segmentation method in an environment with little training data. In the training phase, we obtained the center of the normal metric vector of the input image through the metric embedding model and metric loss, while in the test stage, we detected the mura defect based on the center of the normal metric vector. The experimental results show that the proposed method has higher detection accuracy than the previous method in an environment with few training data.
{"title":"Mura Defect Detection on Compact Camera Module (CCM) Using Metric Learning","authors":"Y. Kim, T. Park","doi":"10.1109/CASE48305.2020.9216886","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9216886","url":null,"abstract":"The Compact Camera Module (CCM) is a device used for various compact electronic devices such as notebooks, smartphones, etc. Various defects occur in the manufacturing process, such as scratches, stamps, and mura. Most notably, mura defect detection is the most challenging issue because of how normal it appears. With this, various methods based on deep learning have been developed to detect mura defects. However, previous research assumes that there is a substantial amount of training data. Therefore, classification accuracy decreases in an environment wherein it is difficult to obtain a sample of an actual defect. This study proposes a metric learning-based mura defect detection method with higher classification accuracy than the previous semantic segmentation method in an environment with little training data. In the training phase, we obtained the center of the normal metric vector of the input image through the metric embedding model and metric loss, while in the test stage, we detected the mura defect based on the center of the normal metric vector. The experimental results show that the proposed method has higher detection accuracy than the previous method in an environment with few training data.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126712342","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-08-01DOI: 10.1109/CASE48305.2020.9216972
Hub Ali, Gang Xiong, Huaiyu Wu, Bin Hu, Zhen Shen, Hongxing Bai
In this paper we consider a problem in task execution for multi-robot trajectory planning with collision avoidance in a shared working environment. Consider two or more robots generating trajectories towards their respective goal positions. The collision may occur if their trajectory coordinates are intersecting at a point or follow the same path segment simultaneously. The central planner is introduced to control robot motion in the collision state and to reduce the complexity of the multi-robot path planning system. The global path for every robot is generated by the $mathrm{A}^{*}$ algorithm in a grid-based environment. The path has presented a sequence of optimal grid numbers and later transformed into Cartesian coordinates for smooth trajectory generation. The central planner takes an optimal grid sequence for every robot to analyze the collision state according to its cost value. It regenerates the trajectories to minimize the complexity cost value and replaces the previous trajectory based on minimum cost value. In the collision state, the central planner allows one robot at a time to pass along the conflict path segment and hold others in queue at a safety offset distance until the previous robot passes safely. The algorithm has been applied to robots working in a shared environment in complex maps and the simulations is performed with MATLAB to calculate the efficiency of this approach for handling collision states in a multi-robot path planning system.
{"title":"Multi-robot Path Planning and Trajectory Smoothing","authors":"Hub Ali, Gang Xiong, Huaiyu Wu, Bin Hu, Zhen Shen, Hongxing Bai","doi":"10.1109/CASE48305.2020.9216972","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9216972","url":null,"abstract":"In this paper we consider a problem in task execution for multi-robot trajectory planning with collision avoidance in a shared working environment. Consider two or more robots generating trajectories towards their respective goal positions. The collision may occur if their trajectory coordinates are intersecting at a point or follow the same path segment simultaneously. The central planner is introduced to control robot motion in the collision state and to reduce the complexity of the multi-robot path planning system. The global path for every robot is generated by the $mathrm{A}^{*}$ algorithm in a grid-based environment. The path has presented a sequence of optimal grid numbers and later transformed into Cartesian coordinates for smooth trajectory generation. The central planner takes an optimal grid sequence for every robot to analyze the collision state according to its cost value. It regenerates the trajectories to minimize the complexity cost value and replaces the previous trajectory based on minimum cost value. In the collision state, the central planner allows one robot at a time to pass along the conflict path segment and hold others in queue at a safety offset distance until the previous robot passes safely. The algorithm has been applied to robots working in a shared environment in complex maps and the simulations is performed with MATLAB to calculate the efficiency of this approach for handling collision states in a multi-robot path planning system.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126323832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-08-01DOI: 10.1109/CASE48305.2020.9216869
Rashmi Ballamajalu, M. Li, F. Sahin, C. Hochgraf, R. Ptucha, M. Kuhl
Autonomous mobile robots are taking on more tasks in warehouses, speeding up operations and reducing accidents that claim many lives each year. This paper proposes a dynamic path planning algorithm, based on $mathrm{A}^{*}$ search method for large autonomous mobile robots such as forklifts, and generates an optimized, time-efficient path. Simulation results of the proposed turn and orientation sensitive $mathrm{A}^{*}$ algorithm show that it has a 94% success rate of computing a better or similar path compared to that of default $mathrm{A}^{*}$. The generated paths are smoother, have fewer turns, resulting in faster execution of tasks. The method also robustly handles unexpected obstacles in the path.
{"title":"Turn and orientation Sensitive A* for Autonomous Vehicles in Intelligent Material Handling Systems","authors":"Rashmi Ballamajalu, M. Li, F. Sahin, C. Hochgraf, R. Ptucha, M. Kuhl","doi":"10.1109/CASE48305.2020.9216869","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9216869","url":null,"abstract":"Autonomous mobile robots are taking on more tasks in warehouses, speeding up operations and reducing accidents that claim many lives each year. This paper proposes a dynamic path planning algorithm, based on $mathrm{A}^{*}$ search method for large autonomous mobile robots such as forklifts, and generates an optimized, time-efficient path. Simulation results of the proposed turn and orientation sensitive $mathrm{A}^{*}$ algorithm show that it has a 94% success rate of computing a better or similar path compared to that of default $mathrm{A}^{*}$. The generated paths are smoother, have fewer turns, resulting in faster execution of tasks. The method also robustly handles unexpected obstacles in the path.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"43 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120949123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-08-01DOI: 10.1109/CASE48305.2020.9217031
Ameena K. Ashraf, Meenakshi D'Souza, R. Jetley
Industrial robots are used in manufacturing industries for tasks that can be automated and work with a controller within a tightly integrated real-time platform. Since they work with humans and other robots, they are safety critical in nature, making testing and verification important tasks in their software development life cycle. We propose coverage criteria for white-box testing of programs that automate tasks of industrial robots and develop a test case generation framework to automatically generate test cases achieving the coverage criteria. A proto-type of our framework has been developed for Rapid, a proprietary programming language for ABB’s industrial robots. Our coverage criteria and framework can be applied to other similar programming languages for industrial robots too, requiring very little customization.
{"title":"Coverage Criteria based Testing of Industrial Robots","authors":"Ameena K. Ashraf, Meenakshi D'Souza, R. Jetley","doi":"10.1109/CASE48305.2020.9217031","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9217031","url":null,"abstract":"Industrial robots are used in manufacturing industries for tasks that can be automated and work with a controller within a tightly integrated real-time platform. Since they work with humans and other robots, they are safety critical in nature, making testing and verification important tasks in their software development life cycle. We propose coverage criteria for white-box testing of programs that automate tasks of industrial robots and develop a test case generation framework to automatically generate test cases achieving the coverage criteria. A proto-type of our framework has been developed for Rapid, a proprietary programming language for ABB’s industrial robots. Our coverage criteria and framework can be applied to other similar programming languages for industrial robots too, requiring very little customization.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121251029","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-08-01DOI: 10.1109/CASE48305.2020.9216975
M. Inui, Kouhei Nishimiya, Nobuyuki Umezu
Herein, we propose a novel technique, referred to as “accessibility map,” to aid tool path computation for five-axis machining. In tool path computation, two problems must be solved: determination of the tool position and determination of its posture. Our technique is useful for the latter task. The posture of the tool is determined so that a certain clearance can be ensured between the tool and the mold surface, to prevent collision between them. A smooth posture change in the machining process must also be considered while determining the posture. The accessibility map records the potential posture information that can be used by the tool in mold surface machining. The use of the proposed technique can reduce the cost for determining the tool posture in the tool path computation for five-axis machining.
{"title":"Accessibility Map for Assisting Cutter Posture Determination in Five-Axis Mold Machining *","authors":"M. Inui, Kouhei Nishimiya, Nobuyuki Umezu","doi":"10.1109/CASE48305.2020.9216975","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9216975","url":null,"abstract":"Herein, we propose a novel technique, referred to as “accessibility map,” to aid tool path computation for five-axis machining. In tool path computation, two problems must be solved: determination of the tool position and determination of its posture. Our technique is useful for the latter task. The posture of the tool is determined so that a certain clearance can be ensured between the tool and the mold surface, to prevent collision between them. A smooth posture change in the machining process must also be considered while determining the posture. The accessibility map records the potential posture information that can be used by the tool in mold surface machining. The use of the proposed technique can reduce the cost for determining the tool posture in the tool path computation for five-axis machining.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123742838","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-08-01DOI: 10.1109/CASE48305.2020.9216748
Runsen Wang, Yilan Shen, Weihao Wang, Leyuan Shi
Motivated by the heat-treating process in a launch vehicles manufacturing plant, we study a two-stage scheduling problem with limited waiting time where the first stage is a batch processor and the second stage is a discrete machine. A mixed-integer programming model is developed and two lower bounds are derived to measure the performance of proposed algorithms. An efficient heuristic together with worst-case analysis is also proposed. Genetic Programming approaches are applied to the flow-shop scheduling problem. Numerical results demonstrate that the proposed algorithms perform better than other meta-heuristics in different production scenarios.
{"title":"Formulation and Methods for a Class of Two-stage Flow-shop Scheduling Problem with the Batch Processor","authors":"Runsen Wang, Yilan Shen, Weihao Wang, Leyuan Shi","doi":"10.1109/CASE48305.2020.9216748","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9216748","url":null,"abstract":"Motivated by the heat-treating process in a launch vehicles manufacturing plant, we study a two-stage scheduling problem with limited waiting time where the first stage is a batch processor and the second stage is a discrete machine. A mixed-integer programming model is developed and two lower bounds are derived to measure the performance of proposed algorithms. An efficient heuristic together with worst-case analysis is also proposed. Genetic Programming approaches are applied to the flow-shop scheduling problem. Numerical results demonstrate that the proposed algorithms perform better than other meta-heuristics in different production scenarios.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122673583","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：