Robotic Assembly Research Articles

Development of an automated reconfigurable robotic airplane fuselage panel final assembly system using state-of-the-art automation technologies

ABSTRACT Airspace companies regularly incorporate state-of-the-art automation technologies into their aircraft assembly systems to reduce lead times and manufacturing costs and improve product quality in their assembly plants. Rapid advances in assembly automation, robotics, material handling, measurement in the assembly processes, and systematic design methodologies require constant consideration of new applications and technologies in assembly systems’ design studies for airplane structures such as fuselage panels. Such a design study is performed in this study to enable the formation of an automated, reconfigurable and robotic fuselage panel final assembly system. The authors’ extensive review of the literature and catalogs reveals that stringer positioning robots, 3D projection devices for fastener position controls on the panels, reconfigurable fixtures for holding the panels, mobile refill friction stir spot joining robots to assemble clips to frames, robotic measurement systems, and modular crane for material handling can be used as state-of-the-art automation technologies in an automated and reconfigurable fuselage panel final assembly system. The proposed automated, reconfigurable, and robotic fuselage panel final assembly system provides an increase in its performance of adaptation level to the changes in the panel types, customers’ order quantities, and suppliers’ and customers’ delivery dates.

Deformation of Flexible Parts in Robotic Assembly

Deformation of Flexible Parts in Robotic Assembly

Human–Robot Collaboration Framework Based on Impedance Control in Robotic Assembly

Human–robot (HR) collaboration (HRC) is an emerging research field because of the complementary advantages of humans and robots. An HRC framework for robotic assembly based on impedance control is proposed in this paper. In the HRC framework, the human is the decision maker, the robot acts as the executor, while the assembly environment provides constraints. The robot is the main executor to perform the assembly action, which has the position control, drag and drop, positive impedance control, and negative impedance control modes. To reveal the characteristics of the HRC framework, the switch condition map of different control modes and the stability analysis of the HR coupled system are discussed. In the end, HRC assembly experiments are conducted, where the HRC assembly task can be accomplished when the assembling tolerance is 0.08 mm or with the interference fit. Experiments show that the HRC assembly has the complementary advantages of humans and robots and is efficient in finishing complex assembly tasks.

Towards Task-Specific Modular Gripper Fingers: Automatic Production of Fingertip Mechanics

The adaption of robotic assembly lines to new products is generally slow and costly, binding the economical usage of a single line to a few products manufactured in masses. An important time factor is the adaption of the assembly robot's gripper fingers to the new product components - since finger design, production, and mounting is done manually. In this letter, we introduce an approach for automatic task-specific fingertip production and application. Our system is potentially able to reduce the assembly line customization time mentioned above by automatically printing customized fingertips onto a pre-produced finger-base and storing them in a dedicated finger library before the product assembly process begins. The assembly robot can then autonomously load and use these produced and stored fingers for the designated manipulation task by utilizing a specially developed quick finger exchange system. The setup is experimentally validated by conducting automatic production of three different fingertips and executing grasp-stability tests as well as multiple pick- and insertion tasks, with and without position offsets - using these fingertips. The proposed approach, indeed, goes beyond fingertip production and serves as a foundation for a fully automatic fingertip design, production, and application pipeline.

Built On-orbit Robotically assembled Gigatruss (BORG): A mixed assembly architecture trade study.

This paper explores a mixed assembly architecture trade study for a Built On-orbit Robotically assembled Gigatruss (BORG). Robotic in-space assembly (ISA) and servicing is a crucial field to expand endeavors in space. Currently, large structures in space are commonly only deployable and must be efficiently folded and packed into a launch vehicle (LV) and then deployed perfectly for operational status to be achieved. To actualize being able to build increasingly large structures in space, this scheme becomes less feasible, being constrained by LV volume and mass requirements. ISA allows the use of multiple launches to create even larger structures. The common ISA proposals consist of either strut-by-strut or multiple deployable module construction methodologies. In this paper, a mixed assembly scheme is explored and a trade study is conducted on its possible advantages with respect to many phases of a mission: 1) manufacturing, 2) stowage and transport, 3) ISA, and 4) servicing. Finally, a weighted decision matrix was created to help compare the various advantages and disadvantages of different architectural schemes.

Research on robotic assembly of gear motors (Stator recognition using keypoint matching and stator insertion using contact position estimation)

Research on robotic assembly of gear motors (Stator recognition using keypoint matching and stator insertion using contact position estimation)

Long-Horizon Multi-Robot Rearrangement Planning for Construction Assembly

Robotic assembly planning enables architects to explicitly account for the assembly process during the design phase, and enables efficient building methods that profit from the robots' different capabilities. Previous work has addressed planning of robot assembly sequences and identifying the feasibility of architectural designs. This paper extends previous work by enabling planning with large, heterogeneous teams of robots. We present a planning system which enables parallelization of complex task and motion planning problems by iteratively solving smaller subproblems. Combining optimization methods to solve for manipulation constraints with a sampling-based bi-directional space-time path planner enables us to plan cooperative multi-robot manipulation with unknown arrival-times. Thus, our solver allows for completing subproblems and tasks with differing timescales and synchronizes them effectively. We demonstrate the approach on multiple case-studies to show the robustness over long planning horizons and scalability to many objects and agents of our algorithm. Finally, we also demonstrate the execution of the computed plans on two robot arms to showcase the feasibility in the real world.

Digital twin-based multi-level task rescheduling for robotic assembly line

Assembly is a critical step in the manufacturing process. Robotic assembly technology in automatic production lines has greatly improved the production efficiency. However, in assembly process, dynamic disturbances such as processing time change and advance delivery may occur, which cause the scheduling deviation. Traditional scheduling methods are not sufficient to meet the real-time and adaptive requirements in smart manufacturing. Digital twin (DT) has the characteristics of virtual-reality interaction and real-time mapping. In this paper, we propose a DT-based framework of task rescheduling for robotic assembly line (RAL) and its key methodologies, thus to realize the timely and dynamic adjustment of scheduling plan under uncertain interferences. First, a DT model of RAL task rescheduling composed of physical entity (PE), virtual entity (VE), and virtual-reality interaction mechanism is proposed. Then, a mathematical model is established. By analyzing the adaptive objective thresholds from the perspectives of event trigger and user demand trigger, a DT-driven multi-level (production unit level and line level) rescheduling strategy is proposed. Taking both the computing time and solution quality into consideration, the precedence graph is introduced to propose a rescheduling approach based on an improved discrete fireworks algorithm. Finally, the effectiveness of the proposed model and approach are verified by task scheduling experiments of RAL.

Resource reconfiguration and optimization in brownfield constrained Robotic Assembly Line Balancing Problems

Successful operation of an assembly line requires balancing work among resources and stations of the line to minimize costs, a problem known as the Assembly Line Balancing Problem (ALBP). Most work in literature considers new production facilities where no resources are available beforehand, known as a greenfield approach. However, reconfiguration required by volatile market demands necessitates assembly line and production capability changes. This reconfigurable production paradigm imposes new constraints on the ALBP. In this paper, we propose an integer-programming-based optimization for solving the dynamic resource reconfiguration for automatic assembly lines. We evaluate our approach on a newly developed multi-cost resource-constrained reconfiguration benchmark dataset, which includes information of an already existing line. Our model achieves, on average, a 1.9× better total assembly line cost compared to an optimized greenfield approach. However, it compromises the number of workstations and line efficiency. This model attempts to enable reconfigurable production and decrease production costs in automatic assembly lines while increasing sustainability.

Deep Learning Framework for Controlling Work Sequence in Collaborative Human–Robot Assembly Processes

The human-robot collaboration (HRC) solutions presented so far have the disadvantage that the interaction between humans and robots is based on the human's state or on specific gestures purposely performed by the human, thus increasing the time required to perform a task and slowing down the pace of human labor, making such solutions uninteresting. In this study, a different concept of the HRC system is introduced, consisting of an HRC framework for managing assembly processes that are executed simultaneously or individually by humans and robots. This HRC framework based on deep learning models uses only one type of data, RGB camera data, to make predictions about the collaborative workspace and human action, and consequently manage the assembly process. To validate the HRC framework, an industrial HRC demonstrator was built to assemble a mechanical component. Four different HRC frameworks were created based on the convolutional neural network (CNN) model structures: Faster R-CNN ResNet-50 and ResNet-101, YOLOv2 and YOLOv3. The HRC framework with YOLOv3 structure showed the best performance, showing a mean average performance of 72.26% and allowed the HRC industrial demonstrator to successfully complete all assembly tasks within a desired time window. The HRC framework has proven effective for industrial assembly applications.

КОНСТРУКТОРСКО-ТЕХНОЛОГИЧЕСКИЕ РЕШЕНИЯ АДДИТИВНОГО ПРОИЗВОДСТВА КОРПУСНЫХ ДЕТАЛЕЙ МКА НК

In this article, research is carried out, technological recommendations are developed, including the choice of material, design solutions for hull parts of small spacecraft NC, taking into account the possibility of their manufacture by additive manufacturing methods and further robotic assembly on a turnkey basis.

An Efficient Robot Precision Assembly Skill Learning Framework Based on Several Demonstrations

This paper proposes an efficient robot assembly skill learning framework based on only a few demonstrations. The assembly skill learning process consists of two phases, e.g., the pre-training phase and the self-learning phase. In pre-training phase, the assembly networks are initialized from demonstration data. A novel data augmentation model based on state transition model is designed, which only requires several human demonstrations to learn the parameters of the model and reduces the cost of demonstration data collection in pre-training. In self-learning phase, the pre-trained assembly networks are further optimized by a hybrid exploration strategy in assembly environment, which explores both parameter space and action space to increase exploration efficiency. On par with the learning framework, a fuzzy reward function balancing the efficiency and compliance of assembly is elaborately designed to evaluate action’s performance in assembly skill self-learning process. Series of physical experiments were well conducted on a sophisticated assembly platform to verify the effectiveness of the proposed efficient robot assembly skill learning framework. Experimental results demonstrate that the learning efficiency of the proposed framework is at least three times as efficient as the state-of-art methods, while the skill performance outperforms the state-of-art by more than 50%. Note to Practitioners—The motivation of this paper is to develop a skill learning framework to achieve efficient assembly skill learning for robot in real-world system. The proposed framework is only based on several demonstrations, which shows high practicability for robot skill learning. The self-learning method is dexterously used to optimize the learned assembly skill from demonstrations since the limited space of demonstrations. Besides, the hybrid exploration strategy and fuzzy reward strategy are well designed to improve the behavior of self-learning. The proposed framework can improve the efficiency and performance of robot assembly learning skill. It is extremely important for robot working in practical applications.

РАЗРАБОТКА ТЕХНОЛОГИИ 3D ПЕЧАТИ КОРПУСНЫХ ДЕТАЛЕЙ МКА НК

In this article, research is being carried out, a technological process is being developed, including the choice of material, the choice of equipment for the production of body parts for small spacecraft NC by the additive manufacturing method for further robotic assembly.

A Geometry-Enhanced 6D Pose Estimation Network With Incomplete Shape Recovery for Industrial Parts

Accurate and robust 6-DOF (6D) pose estimation from a single RGB image and depth map (RGB-D) image is an essential task of intelligent manufacturing, such as robot assembly and digital twin. However, incomplete and noisy 3-D data acquired from depth sensors make the task challenging, especially for various industrial parts without sufficient textures, where the occlusion further exacerbates the problem. To tackle this issue, this article proposes a geometry-enhanced network with incomplete shape recovery (GER-Net) to estimate the 6D pose of industrial parts. First, an incomplete 3-D shape recovery (ISR) module with a learnable shape protection (SP) layer is introduced to recover the complete 3-D geometry shapes of raw point clouds obtained from depth measurements. Subsequently, the multimodal features extracted from raw RGB-D data are enhanced with the geometry information from the recovered point cloud via multiscale concatenation and recurrent forward fusion in the point cloud space. In this way, the enhanced RGB-D representations contribute to the regression of accurate 6D pose. Experiments on two popular benchmark datasets (LineMOD and Occlusion-LineMOD) show that the proposed approach achieves state-of-the-art performance. Furthermore, a real-world low-texture industrial part dataset industrial texture-less machined and 3-D-printed parts (ITM3D) is presented to fully validate the effectiveness of our method, where it also achieves the best performance with remarkable accuracy and robustness.

平行スティック指汎用ハンドによるトレイ上の仕切りに接した円柱状部品のロバスト把持戦略の計画

In recent years, a jig-less robotic assembly system is desired as a lean production system in the manufacturing industry. In jig-less assembly, it is assumed that parts are supplied on a parts tray. However, if the parts are placed in a corner of the tray or along the partitions of the tray, it is difficult to grasp the parts with a versatile robotic hand due to the interference between the fingers of the hand and the tray. In this paper, we address this issue for a cylindrical part, which is frequently handled in actual assembly tasks, and propose a method to plan a robust grasping strategy of the part against the uncertainty in its position, utilizing pushing operation with a versatile robotic hand with parallel stick fingers.

Optimal robotic assembly sequence planning with tool integrated assembly interference matrix

Abstract Manufacturing industries are looking for efficient assembly planners that can swiftly develop a practically feasible assembly sequence while keeping costs and time to a minimum. Most assembly sequence planners rely on part relations in the virtual environment. Nowadays, tools and robotic grippers perform most of the assembly tasks. Ignoring the critical aspect renders solutions practically infeasible. Additionally, it is vital to test the feasibility of positioning and assembling components while employing robotic grippers and tools prior to their implementation. This paper presents a novel concept named by considering both part and tool geometry to propose “tool integrated assembly interference matrices” (TIAIMs) and a “tool integrated axis-aligned bounding box” (TIAABB) to generate practically feasible assembly sequence plans. Furthermore, the part-concatenation technique is used to determine the best assembly sequence plans for an actual mechanical component. The results show that the proposed approach effectively and efficiently deals with real-life industrial problems.

High-Precision Monocular Vision Guided Robotic Assembly Based on Local Pose Invariance

High-Precision Monocular Vision Guided Robotic Assembly Based on Local Pose Invariance

Error Correction in Robotic Assembly Planning From Graphical Instruction Manuals

Error Correction in Robotic Assembly Planning From Graphical Instruction Manuals

Benchmark of the Physics Engine MuJoCo and Learning-based Parameter Optimization for Contact-rich Assembly Tasks

Digital simulation tools are used throughout the entire product development cycle, from designing components using finite element methods to simulating their assembly and planning their production. Especially in research, physics simulators and engines such as MuJoCo are increasingly used for rapid data generation in training machine learning models. The quality of the training data is crucial for successful training and the subsequent deployment of the models in real-world applications. The presented work reports on a systematic benchmark of the physics engine MuJoCo. Representative processes in robotic assembly applications are carried out in simulation and on a physical testbed. The results are compared, focusing on the robot arm's pose and the acting contact forces during the assembly processes using Minimal Jump Cost. Subsequently, a deep reinforcement learning agent takes over the simulation's parameterization, and a first comprehensive system for the process-specifc training of simulation parameters is developed and evaluated to increase the data quality and to partially encapsulate the setup effort involved in digital simulation, aiding offline design and validation. The approach results in overall 8% less dissimilar simulations but not in all the individual scenarios.

Digital Shadows for Robotic Assembly in the World Wide Lab

Due to the lacking standardisation of Digital Shadow (DS) of changeable assembly processes, these processes have not yet been fully integrated into the World Wide Lab (WWL). We propose generalising, standardising, and using Behaviour Trees (BTs) as standard DS for assembly in the WWL. A BT models processes in a modular, human-readable tree structure that has shown great success in many applications. BT monitor task execution giving real-time feedback to their operators. We show that BTs cross several developmental milestones of DSs and give future recommendations for further development and integration into the WWL.