Robust assembly sequence generation in a Human-Robot Collaborative workcell by reinforcement learning

Human-Robot Collaborative (HRC) workcells could enhance the inclusive employment of human workers regardless their force or skills. Collaborative robots not only substitute humans in dangerous and heavy tasks, but also make the related processes within the reach of all workers, overcoming lack of skills and physical limitations. To enable the full exploitation of collaborative robots traditional robot programming must be overcome. Reduction of robot programming time and worker cognitive effort during the job become compelling requirements to be satisfied. Reinforcement learning (RL) plays a core role to allow robot to adapt to a changing and unstructured environment and to human undependable execution of repetitive tasks. The paper focuses on the utilization of RL to allow a robust industrial assembly process in a HRC workcell. The result of the study is a method for the online generation of robot assembly task sequence that adapts to the unpredictable and inconstant behavior of the human co-workers. The method is presented with the help of a benchmark case study.

Process Knowledge Integrated Assembly Sequence Planning for Control Panel

Completely automated assembly sequence planning for control panels is proposed. The proposed algorithm generates the manufacturing bill of material for the assembly processes and total assembly sequence. The algorithm integrates the knowledge of assembly process into a near optimum assembly sequence generation.

Virtuelle Demontage für XL-Produkte/Assembly Sequence Generation for XL-Products – Virtual Disassembly for High Numbers of Components

Aufgrund der hohen Komplexität und Individualität von XL-Produkten ist der Aufwand einer manuellen Montagereihenfolgeplanung derzeit zu hoch, weshalb mögliche Flexibilitätspotenziale eingebüßt werden. Assembly-by-Disassembly-Algorithmen können die Reihenfolgeplanung automatisieren, wodurch die Performance für komplexe Produkte verbessert wird. Ein Ansatz zur Verringerung der Rechenzeit durch Analyse der Bounding-Box-Projektionen wird vorgestellt und validiert. Anhand von Beispielbaugruppen wird eine signifikante Senkung der Rechenzeit nachgewiesen. The effort of an extensive assembly sequence planning is usually not justified for individual XL-products with low lot sizes. An improved performance of assembly-by-disassembly algorithms for complex products could efficiently automate this process. An approach to reduce the computing time by analyzing bounding box projections is presented and validated. Example assemblies with a high number of components are used for demonstrating a significant reduction of the computing time.

Automatically generating assembly sequences with an ontology-based approach

Purpose The purpose of this paper is to present and develop an ontology-based approach for automatic generation of assembly sequences. Design/methodology/approach In this approach, an assembly sequence planning ontology is constructed to represent the structure and interrelationship of product geometry information and assembly process information. In the constructed ontology, certain reasoning rules are defined to describe the knowledge and experience. Based on the ontology with reasoning rules, the algorithm for automatically generating assembly sequences is designed and implemented. Findings The effectiveness of this approach is verified via applying it to generate the assembly sequences of a gear reducer. Originality/value The main contribution of the paper is presenting and developing an ontology-based approach for automatically generating assembly sequences. This approach can provide a feasible solution for the issue that mathematics-based assembly sequence generation approaches have great difficulty in explicitly representing assembly experience and knowledge.

Subassembly Detection and Optimal Assembly Sequence Generation through Elephant Search Algorithm

Most of the engineering products are made with multiple components. The products with multiple subassemblies offer greater flexibility for parallel assembly operation and also disassembly operation during its end of life. Assembly cost and time can be minimized by reducing the number of assembly levels. In this paper, Elephant search algorithm is used to perform Optimal Assembly Sequence Planning (OASP) in order to minimize the number of assembly levels. Subassembly identification technique is used as an integral part of algorithm to identify the parallel assembly possibilities. The proposed method is implemented on industrial products and a detailed comparative assessment has been made with suitable product illustrations to corroborate the efficiency.