Search

Nowadays industrial robots have been increasingly widely deployed across various sectors and assembly tasks are seen as one of the dominant application fields. The assembly tasks, as the critical process in manufacturing, are still challenging for the robot because of the complex contact state between the robot and the environment (i.e. assembly components). In the assembly task, the robot should switch its controller from a non-contact mode to a contact-rich mode when the contact condition changes, where compliant behaviour is necessary for robustness to uncertain contact and safety of physical interaction. This paper proposes a deep reinforcement learning (DRL) method to achieve such compliance using variable stiffness compliant control. Concretely, a Cartesian compliant controller is built on a virtual dynamics model with a variable non-diagonal stiffness matrix to derive desired motion that reacts with the external force/torque. Upon that, a deep deterministic policy gradient (DDPG)-based agent is deployed to fine-tune such a non-diagonal stiffness matrix. After error-and-trial learning, robots can handle changes in contact state in assembly tasks without any pause and switching its controller mode, thus increasing task efficiency and compliance. The simulation and experiments show that our method allows robots to complete assembly tasks safely and efficiently under noisy observation. [ABSTRACT FROM AUTHOR]

The planetary construction is necessary for long-term scientific deep space exploration and resource utilization in the future. The planetary robotic assembly control is a key technology that must be broken through in future planetary surface construction. The paper focuses on the most representative dual peg-in–hole assembly, which has sufficiently complex contact interaction, wide range of applications and good method portability. To address the challenges brought by the unstructured planetary environment and the features of the construction tasks, the paper proposes an end-to-end deep reinforcement learning and control method with multimodal perception for planetary robotic assembly tasks. A staged reward function based on the visual virtual target point for policy learning is designed. The effectiveness and feasibility of the proposed control method have been verified through simulation experiments and ground real robot experiments. It provides a feasible control method of robotic operations for future planetary surface construction. [ABSTRACT FROM AUTHOR]

Space telescopes have been instrumental in enlightening our understanding of the universe, from the iconic Hubble Space Telescope to specialized instruments like Chandra and Kepler. Pushing the frontiers of cosmic exploration, the future of space exploration hinges on modular Large Aperture Space Telescopes (LAST), much larger than the recently launched 6.5 m James Webb Space Telescope, necessitating robotic assembly in orbit. This paper introduces a paradigm shift in astronomical observation by featuring robotic in-orbit assembly of a large aperture space telescope. This review paper starts by tracing the evolution of telescopes and presents a comprehensive overview of the state-of-the-art space telescopes. This paper then reinforces the need for LAST to address the constant clamour for higher-resolution astronomy. While current semi-autonomous robotic manipulators operate from the International Space Station, their limited walking capabilities constrain their workspace, making them unsuitable for the LAST mission. This paper presents a detailed trade-off analysis of the challenges associated with the in-orbit assembly of LAST using candidate robots to understand the technological gaps. Further, the evolution of space robotic manipulators is presented, highlighting design features, advantages, and drawbacks for in-orbit spacecraft servicing and assembly missions. To tackle design and modelling challenges for robotic systems in space, amidst the various perturbations in the extreme space environment, linear and non-linear control systems necessary for achieving ultra-high precision performance are also discussed. This paper advances the walking space manipulator technology by introducing the next generation of walking space manipulators – the End-Over-End Walking Robot (E-Walker). The dexterous and modular design of the E-Walker makes it an ideal candidate for missions involving assembly, manufacturing, servicing, and maintenance. [ABSTRACT FROM AUTHOR]

Imaging systems larger than the James Webb Space Telescope will enable unprecedented astronomy in the future. Larger aperture space-based imagers will also support next-generation Earth Observation missions for national security and disaster monitoring. However, launching and operating such large telescopes in the poses several practical challenges. A key challenge is that mirrors with apertures larger than 3 m cannot be monolithically manufactured so a segmented design is utilized to achieve primary mirror apertures. Even if larger mirrors could be made, it would be impossible to stow them in fairings of most existing and future launch vehicles. Folded-wing designs to deploy segmented primary mirrors, as done with the James Webb Space Telescope, are one approach to overcoming this volumetric challenge but inappropriate for 25 m apertures considered in this study. This paper presents the concept of operations and mission architectures/analysis for on-orbit assembly of a 25 m aperture telescope operating in the visible waveband of the electromagnetic spectrum capable of 1 m spatial resolution from geostationary orbit. Further, a technology demonstration roadmap towards maturing the robotic assembly technology stack is then presented as precursors to the 25 m imaging system. • Robotic on-orbit assembled large telescopes will enable next-gen imaging. • The paper designs a 25 m aperture space telescope. • In-orbit mass of telescope is ∼ 50 tonnes. • Robotic assembly is architected in a NewSpace lens. • Precursor technology demonstrations are then presented. [ABSTRACT FROM AUTHOR]

According to the UNHCR, 117.2 million people have been displaced in 2023, with the rate and scale of displacement surpassing the resources available to assist those impacted. Modular construction is favored over traditional methods to meet the urgent demand for affordable housing as it overcomes challenges like long project timelines, high costs, and safety and environmental issues. However, manual assembly is often slow and prone to errors, resulting in inefficiencies and higher costs. While advanced technologies could improve the process, there is limited research on automating assembly in modular construction. This research aims to assess how automation affects the time efficiency and cost of the modular construction process, aiming to improve affordable housing production by automating modular construction. The research follows a quantitative approach, collecting data through simulation to evaluate the effectiveness of integrating robotics in modular construction assembly processes. It compares the performance of automated and manual assembly processes, focusing on resource utilization, time savings, and cost implications. The results reveal that modular manufacturing automated assembly offers faster assembly times and improved cost efficiency, leading to higher productivity and lower overall construction costs. By conducting a detailed analysis, this research provides insights that can guide the integration of automation into modular construction manufacturing. [ABSTRACT FROM AUTHOR]

Uncertainties in robotic assembly can substantially influence the quality of assembly task planning, often resulting in suboptimal solutions. It is crucial to account for these uncertainties when developing assembly task plans that are both efficient and practical for multi-part products. To address such issues, the proposed method integrates the NelderMead simplex algorithm with the Class Topper Optimisation Algorithm to create a hybrid NelderMead Class Topper Optimisation Algorithm. This study uses a vibration generator as an example to illustrate the application of the proposed method. Ensuring tool accessibility is emphasised, and the assembly tasks are initialised accordingly. The feasibility of these tasks is determined using liaison and tool-integrated geometric feasibility predicate analysis. Multiple criteria are considered to achieve the most efficient robotic assembly task planning, including part reorientation, gripper or tool change and the energy required to assemble the part. The effectiveness and robustness of the proposed optimisation algorithm are demonstrated by comparing it with other algorithms, such as the teaching-learning-based algorithm, the genetic algorithm, the bees algorithm and the particle swarm optimisation algorithm. The results have shown that the proposed approach is highly effective for real-industrial relevant problems. [ABSTRACT FROM AUTHOR]

The Agile Robotics for Industrial Automation Competition (ARIAC) was established to advance flexible manufacturing, aiming to increase the agility of robotic assembly systems in unstructured and dynamic industrial environments. ARIAC 2023 introduced eight agility challenges involving faulty parts, flipped parts, faulty grippers, robot malfunctions, sensor blackouts, high-priority orders, insufficient parts, and human safety. Given the unpredictability of these scenarios, it is impractical to develop a specific strategy for each possible situation. To address these issues, this paper presents a hierarchical framework for autonomous robotic task generation and execution in dynamic scenarios. The framework is divided into a task level and an execution level. Initially, an immediate task management strategy is adopted at the task level, which reasonably decomposes dynamic tasks and allocates short-term tasks to the floor robot and ceiling robot. Later, at the execution level, each robot is designed with an agent architecture that combines PDDL planning with the quick response of behavior trees. Finally, the effectiveness and practicality of the proposed framework were thoroughly validated in ARIAC 2023. [ABSTRACT FROM AUTHOR]

In the transition from Industry 4.0 to Industry 5.0, the integration of human-centric considerations into manufacturing processes becomes vital. This study advances beyond conventional Industry 4.0 frameworks by introducing a novel fatigue model that emphasizes ergonomic risk management during the design phase of robotic assembly lines. Utilizing a hybrid model that employs a fuzzy inference system based on ergonomist knowledge, this fuzzy approach manages the imprecise nature of ergonomic optimization more accurately than deterministic models and effectively reflects real-world complexities. By evaluating fatigue at both task and worker levels, this fuzzy inference mechanism addresses technical aspects through feasibility studies and significantly improves ergonomic outcomes. The integration of supportive robots is explored through scenario-based analysis, highlighting productivity enhancements and substantial ergonomic benefits in line with Industry 5.0's focus on enhancing worker well-being and operational resilience. The proposed heuristic algorithm enables decision-makers to identify the most efficient solutions tailored to individual preferences, showcasing flexibility and real-world applicability. Empirical validation, enriched with synthesized ergonomic-oriented instances, confirms the superiority of this approach in creating more sustainable and ergonomically optimized assembly lines. Implementing this approach is predicted to decrease system costs by up to 47%, particularly advantageous during human resources crises, by reducing ergonomic risk, recovery needs, and additional capacity requirements for fatigue mitigation. This study contributes to the discourse on the practical implications of Industry 5.0 and demonstrates its applicability in designing ergonomically optimized assembly lines that prioritize long-term productivity and worker satisfaction. [ABSTRACT FROM AUTHOR]

Space solar power is an old idea. From its initial suggestion in the 1940s to the first practical concept by Dr. Peter Glaser in 1968, it has been analyzed, studied, and refined many times. Multiple government institutions, including NASA, JAXA, ESA, and CAST have invested significant funds into developing direct space solar power research. In parallel to these direct studies, considerable investment has also flowed into enabling technologies that serve as the cornerstone of current space solar power development concepts, including space solar panels, space hardware manufacturing, low-cost launch, wireless power transfer, robotic assembly, and swarm monitoring/control. In the last few years, space solar power concepts and studies have received increased funding, including non-governmental funding showing a strong positive growth trend. Multiple reports in 2021 and 2022, including from this author, have found that while space solar power has been technically feasible for decades, falling launch and hardware costs have only recently made it economically viable as well. Despite these findings, translation from economic feasibility to economic reality will require additional high-value investment. Sourcing these new funds requires investment context. This technical paper will present a state of the industry report on space solar power, including the total and source distribution of historical investments. It further contextualizes the investments in space solar power with the scale of investment in key technologies and their current technology readiness levels. The methodologies developed for this report and the data sourced are intended to serve as a catalyst, alongside industry feedback, to create a template for ongoing reporting of this growing market sub-sector and ultimately drive the full deployment of this technology. • NASA found in 1979 that Space Solar Power was technically and economically viable. • A half-century later solar power cost has fallen 99.8 %, launch has fallen 97.6 %. • A given solar panel will produce 6–20 times as much energy in space. • Direct investment into space solar power has reached $879 million. • Critical indirect investment, including into solar PV, is in hundreds of billions. [ABSTRACT FROM AUTHOR]

Robotic systems are crucial in modern manufacturing. Complex assembly tasks require the collaboration of multiple robots. Their orchestration is challenging due to tight tolerances and precision requirements. In this work, we set up two Franka Panda robots performing a peg-in-hole insertion task of 1 mm clearance. We structure the control system hierarchically, planning the robots' feedback-based trajectories with a central policy trained with reinforcement learning. These trajectories are executed by a low-level impedance controller on each robot. To enhance training convergence, we use reverse curriculum learning, novel for such a two-armed control task, iteratively structured with a minimum requirements and fine-tuning phase. We incorporate domain randomization, varying initial joint configurations of the task for generalization of the applicability. After training, we test the system in a simulation, discovering the impact of curriculum parameters on the emerging process time and its variance. Finally, we transfer the trained model to the real-world, resulting in a small decrease in task duration. Comparing our approach to classical path planning and control shows a decrease in process time, but higher robustness towards calibration errors. [ABSTRACT FROM AUTHOR]

Featured Application: The presented methodology can be used in all robotic assembly tasks where the camera position changes during operation, such as tasks where the camera is mounted on the robotic arm near the end-effector—for example, in fuse box assembly applications. The increase in positioning accuracy and repeatability allowed the integration of robots in assembly operations using guidance systems (structured applications) or video acquisition systems (unstructured applications). This paper proposes a procedure to determine the measuring plane using a 3D laser camera. To validate the procedure, the camera coordinates and orientation will be verified using robot coordinates. This procedure is an essential element for camera calibration and consists of developing a mathematical model using the least square method and planar regression. The mathematical model is considered necessary as a step towards optimizing the integration of robotic vision systems in assembly applications. A better calibrated camera has the potential to provide better recognition results, which are essential in this field. These improved results can then be used to increase the accuracy and repeatability of the robot. [ABSTRACT FROM AUTHOR]

The Robotic Assembly Line Balancing Problem (RALBP) is a joint optimisation problem that is concerned with assigning both assembly operations and robots to workstations that are placed within a straight line. RALBP-2 is the particular problem where the cycle time, which is the maximum time spent on a workstation by the product being assembled, is minimised while the number of workstations is fixed. Sequence-dependent setup times are considered which raises the problem of sequencing the operations assigned to each workstation. Both the durations of the operations and the setup times depend on the robot. Two different variants are identified from literature. The first variant assumes that, given a set of types of robots, each type of robot can be assigned to multiple workstations without any limitation. Given a set of robots, the second variant forces each robot to be assigned to at most one workstation. Both assumptions are studied in this paper. The particular case of a given giant sequence of operations is solved thanks to a polynomial optimal algorithm. The latter algorithm, called split, is then embedded in a metaheuristic framework that explores the space of giant sequences. Benchmark data sets from literature are considered in the experimental section. A comparative study with other methods from literature shows the competitiveness of the suggested approach. [ABSTRACT FROM AUTHOR]

Rapid urbanization has led to resource shortages, necessitating sustainable approaches in the building industry. This research proposes a preliminary voxel-based modular-architectural design strategy (VMADS), focusing on reusable “H” blocks for component connections and construction. By integrating computational design and robotic fabrication, VMADS enhances precision and efficiency. The framework addresses discrete building theory, prefabrication, and autonomous architecture, emphasizing wood’s anisotropic nature for structural integrity. Experimental results validated VMADS through digital simulations and physical tests, demonstrating its potential to create sustainable, reconfigurable structures and revolutionize construction practices.

Contact state recognition is a critical technology for enhancing the robustness of robotic assembly tasks. There have been many studies on contact state recognition for single-manipulator, single peg-in-hole assembly tasks. However, as the number of pegs and holes increases, the contact state becomes significantly more complex. Additionally, when a tightly coupled multi-manipulator is required, the estimation errors in the contact forces between pegs and holes make contact state recognition challenging. The current state recognition methods have not been tested in such tasks. This paper tested Support Vector Machine (SVM) and several neural network models on these tasks and analyzed the recognition accuracy, precision, recall, and F1 score. An ablation experiment was carried out to test the contributions of force, image, and position to the recognition performance. The experimental results show that SVM has better performance than the neural network models. However, when the size of the dataset is limited, SVM still faces generalization issues. By applying heuristic action, this paper proposes a two-stage recognition strategy that can improve the recognition success rate of the SVM. [ABSTRACT FROM AUTHOR]

In the age of Industry 4.0 and smart manufacturing, traditional production processes are undergoing significant changes due to the integration of advanced technologies like automation, robotics, big data analytics, and machine learning, which are enhancing productivity and manufacturing efficiency. The center of this evolution is the introduction of the digital twin (DT), the digital replicas of physical assets that blend real-time data with advanced analytics and simulations. Ensuring synchronization between the digital replica and its physical counterpart is crucial for successfully implementing digital twins. This paper addresses the challenge of achieving and quantifying synchronization within DTs, focusing on replicating physical system behavior and measuring deviations or delays. The study delves into the critical aspects of synchronization within digital twin applications, focusing on its implications for a robotic assembly system. The research successfully harnessed YOLOv8 to facilitate real-time event tracking and synchronization characterization, highlighting the potential of object detection deep-learning models in enhancing synchronization accuracy and, consequently, the efficiency and reliability of manufacturing processes. [ABSTRACT FROM AUTHOR]

This paper presents a new switchable variable stiffness mechanism (SVSM) aimed at reducing reaction forces in robotic assembly tasks. The introduced switchable variable stiffness device (SVSD) exceeds existing variable stiffness mechanisms (VSMs) by providing a three-degree of freedom. Additionally, it features adaptable switchable springs suitable for various working environments, designed to be lightweight and easily manufacturable using 3D printing materials. A theoretical model of the SVSM was developed, with its accuracy validated through simulations and experimental trials. Furthermore, standard process models for two different assembly task scenarios were also developed and implemented, showcasing the improved assembly performance of the SVSM. [ABSTRACT FROM AUTHOR]

Robots are now widely used in assembly tasks. However, when robots perform the automatic assembly of Multi-Pin Circular Connectors (MPCCs), the small diameter of the pins and the narrow gaps between them present significant challenges. During the assembly process, the robot's end effector can obstruct the view, and the contact between the pins and the corresponding holes is completely blocked, making this task more precise and challenging than the common peg-in-hole assembly. Therefore, this paper proposes a robotic assembly strategy for MPCCs that includes two main aspects: (1) we employ a vision-based Deep Siamese Neural Network (DSNN) model to address the most challenging peg-in-hole alignment problem in MPCC assembly. This method avoids the difficulties of modeling in traditional control strategies, the high training costs, and the low sample efficiency in reinforcement learning. (2) This paper constructs a complete practical assembly system for MPCCs, covering everything from gripping to final screwing. The experimental results consistently demonstrate that the assembly system integrated with the DSNN can effectively accomplish the MPCC assembly task. [ABSTRACT FROM AUTHOR]

On‐orbit close proximity operations involve robotic spacecraft maneuvering and making decisions for a growing number of mission scenarios demanding autonomy, including on‐orbit assembly, repair, and astronaut assistance. Of these scenarios, on‐orbit assembly is an enabling technology that will allow large space structures to be built in situ, using smaller building block modules. However, like many of these scenarios, robotic on‐orbit assembly involves several technical hurdles, such as changing system models. For instance, grappled modules moved by a free‐flying "assembler" robot can cause significant changes in the combined system inertia, which have cascading impacts on motion planning and control portions of the autonomy stack. Further, on‐orbit assembly and other scenarios require collision‐avoiding motion planning, particularly when operating in a "construction site" scenario of multiple assembler robots and structures. Multiple key technologies that address these complicating factors for autonomous microgravity close proximity operations are detailed in this work, in particular: (1) application of global long‐horizon planning, accomplished using offline and online sampling‐based planner options that consider the system dynamics; (2) adaptation of the recently proposed RATTLE information‐aware planning framework for on‐orbit reconfiguration model learning; and (3) connection with robust control tools to provide low‐level control robustness using current system knowledge. These approaches were demonstrated for an autonomous on‐orbit assembly use case by the RElative Satellite sWarming and Robotic Maneuvering (ReSWARM) experiments using NASA's Astrobee robots on the International Space Station. Results of the ReSWARM experiments are provided along with significant operational and implementation detail discussing the practicalities of hardware implementation and unique aspects of working with the Astrobee free‐flyer robots in microgravity. ReSWARM provides a base set of planning and control tools for robotic close proximity operations, demonstrates them in microgravity, and outlines some of the important hardware aspects that future autonomous free‐flyers will need to consider. [ABSTRACT FROM AUTHOR]

In this article, we propose a distributed synchronization solution to achieve decentralized coordination in a system of collaborative robots. This is done by leveraging cloud-based computing and 5G technology to exchange causal ordering messages between the robots, eliminating the need for centralized control entities or programmable logic controllers in the system. The proposed solution is described, mathematically formulated, implemented in software, and validated over realistic network conditions. Further, the performance of the decentralized solution via 5G technology is compared to that achieved with traditional coordinated/uncoordinated cabled control systems. The results indicate that the proposed decentralized solution leveraging cloud-based 5G wireless is scalable to systems of up to 10 collaborative robots with comparable efficiency to that from standard cabled systems. The proposed solution has direct application in the control of producer–consumer and automated assembly line robotic applications. [ABSTRACT FROM AUTHOR]

This research explores the SL-Block system within an architecture framework by embracing building modularity, combinatorial design, topological interlocking, machine learning, and tactile sensor-based robotic assembly. The SL-Block, composed of S and L-shaped tetracubes, possesses a unique self-interlocking feature that allows for reversible joining and the creation of various 2D or 3D structures. In architecture modularity, the high degree of reconfigurability and adaptability of the SL-Block system introduces a new element of interest. Unlike modularization strategies that emphasize large-scale volumetric modules or standardized building components, using small-scale generic building blocks provides greater flexibility in maximizing design variations and reusability. Furthermore, the serial repetition and limited connectivity of building elements reduce the efforts required for bespoke manufacturing and automated assembly. In this article, we present our digital design and robotic assembly strategies for developing dry-jointed modular construction with SL-Blocks. Drawing on combinatorics and graph theory, we propose computational design methods that can automatically generate hierarchical SL-Block assemblies from given shapes. To address the physical complexities of contact-rich assembly tasks, we develop robotics using two distinct methods: pre-programmed assembly and sensor-based reinforcement learning. Through a series of demonstrators, we showcase the ability of SL-Blocks not only to reconfigure conventional building tectonics but also to create new building configurations. [ABSTRACT FROM AUTHOR]

The visual measurement of deep holes in composite material workpieces constitutes a critical step in the robotic assembly of aerospace components. The positioning accuracy of assembly holes significantly impacts the assembly quality of components. However, the complex texture of the composite material surface and mutual interference between the imaging of the inlet and outlet edges of deep holes significantly challenge hole detection. A visual measurement method for deep holes in composite materials based on the radial penalty Laplacian operator is proposed to address the issues by suppressing visual noise and enhancing the features of hole edges. Coupled with a novel inflection-point-removal algorithm, this approach enables the accurate detection of holes with a diameter of 10 mm and a depth of 50 mm in composite material components, achieving a measurement precision of 0.03 mm. [ABSTRACT FROM AUTHOR]

The demands for efficiency and stability in space missions have necessitated the development of sequence planning schemes for on-orbit robotic assembly of space structures. A sequence planning method is proposed in this work based on robotic kinematic analysis and Symbiotic Organisms Search (SOS) algorithm with a diversification strategy. With feasibility as the constraint and assembly cost as the objective function, the assembly sequence planning is regarded as an optimization problem. The assembly relationship constraint is depicted as the dependency between assembly steps represented by a directed acyclic graph. An abstract modeling method based on robotic kinematics is proposed to construct geometric feasibility constraint, accommodating the interference stemming from the multi-degree-of-freedom motion of the robotic system. A diversification strategy is exploited to address the issue of local optima arising from solving the optimal sequence based on SOS. A cost prediction method using previously calculated populations as samples is proposed to reduce the reliance on robotic dynamic analysis for cost calculation. Finally, simulations are carried out to validate the practicability of the proposed method. • The on-orbit robotic assembly sequence planning is modeled as an optimization problem with feasibility constraints. • The dependencies and priorities between steps are considered in the feasibility constraints of multi-DOF robotic motions. • The optimal sequence determination based on Symbiotic Organisms Search is speeded up by a cost prediction method. [ABSTRACT FROM AUTHOR]

This study examines the practicality and limitations of using a FANUC CRX-10 iA/l collaborative robot to assemble a product component, highlighting the trade-offs between increased robotization and reduced manual intervention. Through a detailed case study in the i-Labs laboratory, critical factors affecting precision assembly such as station layout, tooling design and robot programming are discussed. The findings highlight the benefits of robots for nonstop operation, freeing up human operators for higher value tasks despite longer cycle times. In addition, the paper advocates further research into reliable gripping of small components, a current challenge for robotics. The work contributes to open science by sharing partial results and methods that could inform future problem solving in robotic assembly. [ABSTRACT FROM AUTHOR]

In the robot finishing process of the assembly interface of large aerospace cylindrical components (short for assembly interface), to realize the high-precision and high-efficiency pose perception of the large component, an intelligent pose measurement method for the large component is proposed based on binocular vision and priori data. In this method, the global coordinate system of the robot finishing system is initially established using laser tracking measurement method and customized reference plates, giving a unified coordinate transformation datum for the interoperation of the finishing system's subsystems. Then, utilizing deep learning and digital image processing technologies, an algorithm for recognizing and locating key features of the large component is developed, which can realize the identification of key feature types and accurate localization of feature centroids. Following that, the global coordinate of the key feature centroid is determined using the proposed binocular vision three-dimensional (3D) coordinate reconstruction method. Meanwhile, by introducing the priori processing data of the large component to match the 3D reconstruction coordinates of the key feature centroids, the spatial pose of the large component can be calculated with high precision. Finally, the proposed method is experimentally validated using a case study of a large aerospace cylindrical component. Experimental results prove that the proposed method can achieve high-precision pose measurement of the large component, which can provide pose data support for the adjustment or modification of the cutting path of the robot that is generated by the as-designed model of the large component, to ensure the correctness of the robotic machining of the assembly interface, and thus the proposed method can meet the robot finishing needs of the large component. [ABSTRACT FROM AUTHOR]

In this paper, different test cases where robotic arms are tested will be presented. A robotic arm is tested for the gravity effects that can be observed on it. The other robotic arm is tested for how much precision it has by using it to learn to write. The other robotic arm is tested on how well it can function as a solar tracker and how precisely it can function as an energy harvester. On the basis of these tests, the robotic arm's mechanical structure, electronics, and software are put to the test. The software is based on evolutionary software that implements genetic algorithms. The entire command system is also ported to FPGAs (to hardware) to increase speed and response time. [ABSTRACT FROM AUTHOR]

Automated assembly tasks require industrial robots to improve the efficiency of the manufacturing process. Most rigid or flexible objects handled by robots vibrate due to motion and transient disturbance. This work proposes an active vision-based vibration suppression strategy for flexible beams by providing motion to the wrist of a robot during robotic assembly process, which reduces the time to suppress vibration. The proposed method uses a cheap monocular camera to identify objects through a virtual marker and measure their dimensions. Subsequently, finite element method based mathematical model of a flexible beam predicts the maximum error. The proposed second stage controller determines the controller input in terms of wrist motion based on the predicted maximum error. The performance of the controller is assessed through simulations and experiments on metallic beams with different material characteristics and dimensions. The controller suppresses vibration amplitude within a safe limit so that object is inserted into the slot. It was observed from experiments that the controller can reduce vibration amplitude by ~96% in less than 2 s and decrease suppression time up to ~97%. These improvements were achieved without disturbing the internal robot controller. [ABSTRACT FROM AUTHOR]

Shaft sleeve assembly is a common task in industrial manufacturing. The fitting approach for shaft sleeve assembly is usually interference fit, which requires significant contact forces. Conventional assembly methods, though focused on safety, often struggle to achieve high efficiency. Reinforcement learning can effectively select appropriate assembly actions through interaction with the environment, making it well-suited for shaft sleeve assembly tasks. Firstly, a comprehensive workflow for shaft sleeve assembly is formulated, including system initialization, insertion, push, and completion. Our research focuses mainly on the insertion process. Secondly, the core control algorithm adopts a deep reinforcement learning method based on the Actor-Critic architecture. The reward function includes safety reward, step length reward, and step reward. Safety reward ensures assembly security, while step length and step reward enhance assembly efficiency from different perspectives. Finally, real-world experiments on shaft sleeve assembly are conducted, including ablation experiments, parameter tuning experiments on reward function, and comparative experiments with conventional methods. The results of the ablation experiments and parameter tuning experiments indicate that after combining safety reward, step length reward, and step reward, the assembly effect achieves the best, verifying the effectiveness of the proposed reward function. Comparative experimental results demonstrate that our approach not only enhances safety compared to conventional methods but also significantly improves assembly efficiency, indicating the feasibility of this method. [ABSTRACT FROM AUTHOR]

Introduction: Robotic assembly tasks require precise manipulation and coordination, often necessitating advanced learning techniques to achieve efficient and effective performance. While residual reinforcement learning with a base policy has shown promise in this domain, existing base policy approaches often rely on hand-designed full-state features and policies or extensive demonstrations, limiting their applicability in semi-structured environments. Methods: In this study, we propose an innovative Object-Embodiment-Centric Imitation and Residual Reinforcement Learning (OEC-IRRL) approach that leverages an object-embodiment-centric (OEC) task representation to integrate vision models with imitation and residual learning. By utilizing a single demonstration and minimizing interactions with the environment, our method aims to enhance learning efficiency and effectiveness. The proposed method involves three key steps: creating an object-embodiment-centric task representation, employing imitation learning for a base policy using via-point movement primitives for generalization to different settings, and utilizing residual RL for uncertainty-aware policy refinement during the assembly phase. Results: Through a series of comprehensive experiments, we investigate the impact of the OEC task representation on base and residual policy learning and demonstrate the effectiveness of the method in semi-structured environments. Our results indicate that the approach, requiring only a single demonstration and less than 1.2 h of interaction, improves success rates by 46% and reduces assembly time by 25%. Discussion: This research presents a promising avenue for robotic assembly tasks, providing a viable solution without the need for specialized expertise or custom fixtures [ABSTRACT FROM AUTHOR]

Copyright of Ingeniería (0121-750X) is the property of Ingenieria and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The robotic drilling of assembly holes is a crucial process in aerospace manufacturing, in which measuring the normal of the workpiece surface is a key step to guide the robot to the correct pose and guarantee the perpendicularity of the hole axis. Multiple laser displacement sensors can be used to satisfy the portable and in-site measurement requirements, but there is still a lack of accurate analysis and layout design. In this paper, a simplified parametric method is proposed for multi-sensor normal measurement devices with a symmetrical layout, using three parameters: the sensor number, the laser beam slant angle, and the laser spot distribution radius. A normal measurement error distribution simulation method considering the random sensor errors is proposed. The measurement error distribution laws at different sensor numbers, the laser beam slant angle, and the laser spot distribution radius are revealed as a pyramid-like region. The influential factors on normal measurement accuracy, such as sensor accuracy, quantity and installation position, are analyzed by a simulation and verified experimentally on a five-axis precision machine tool. The results show that increasing the laser beam slant angle and laser spot distribution radius significantly reduces the normal measurement errors. With the laser beam slant angle ≥15° and the laser spot distribution radius ≥19 mm, the normal measurement error falls below 0.05°, ensuring normal accuracy in robotic drilling. [ABSTRACT FROM AUTHOR]

Reinforcement learning (RL) has been successfully applied to a wealth of robot manipulation tasks and continuous control problems. However, it is still limited to industrial applications and suffers from three major challenges: sample inefficiency, real data collection, and the gap between simulator and reality. In this paper, we focus on the practical application of RL for robot assembly in the real world. We apply enlightenment learning to improve the proximal policy optimization, an on-policy model-free actor-critic reinforcement learning algorithm, to train an agent in Cartesian space using the proprioceptive information. We introduce enlightenment learning incorporated via pretraining, which is beneficial to reduce the cost of policy training and improve the effectiveness of the policy. A human-like assembly trajectory is generated through a two-step method with segmenting objects by locations and iterative closest point for pretraining. We also design a sim-to-real controller to correct the error while transferring to reality. We set up the environment in the MuJoCo simulator and demonstrated the proposed method on the recently established The National Institute of Standards and Technology (NIST) gear assembly benchmark. The paper introduces a unique framework that enables a robot to learn assembly tasks efficiently using limited real-world samples by leveraging simulations and visual demonstrations. The comparative experiment results indicate that our approach surpasses other baseline methods in terms of training speed, success rate, and efficiency. [ABSTRACT FROM AUTHOR]

With the ever increasing number of active satellites in space, the rising demand for larger formations of small satellites and the commercialization of the space industry (so-called New Space), the realization of manufacturing processes in orbit comes closer to reality. Reducing launch costs and risks, allowing for faster on-demand deployment of individually configured satellites as well as the prospect for possible on-orbit servicing for satellites makes the idea of realizing an in-orbit factory promising. In this paper, we present a novel approach to an in-orbit factory of small satellites covering a digital process twin, AI-based fault detection, and teleoperated robot-control, which are being researched as part of the "AI-enabled Cyber–Physical In-Orbit Factory" project. In addition to the integration of modern automation and Industry 4.0 production approaches, the question of how artificial intelligence (AI) and learning approaches can be used to make the production process more robust, fault-tolerant and autonomous is addressed. This lays the foundation for a later realization of satellite production in space in the form of an in-orbit factory. Central aspect is the development of a robotic AIT (Assembly, Integration and Testing) system where a small satellite could be assembled by a manipulator robot from modular subsystems. Approaches developed to improving this production process with AI include employing neural networks for optical and electrical fault detection of components. Force sensitive measuring and motion training helps to deal with uncertainties and tolerances during assembly. An AI-guided teleoperated control of the robot arm allows for human intervention while a Digital Process Twin represents process data and provides supervision during the whole production process. Approaches and results towards automated satellite production are presented in detail. • An automated production system for modular small satellites is proposed. • Central element is a force-sensitive robotic assembly, integration & testing system. • AI and machine learning approaches are applied to make the process more robust. • A digital process twin supervises the autonomous production. • A multi-modal shared control approach allows human teleoperation if required. [ABSTRACT FROM AUTHOR]

The development of resilience in manufacturing systems has drawn more attention than ever. Using redundant components is one of the key strategies for building and enhancing the resilience of a manufacturing system. However, current redundancy strategies require duplicated machinery employed either in active or in standby status. This in turn causes extra costs in designing and achieving resilience. Achieving an efficient deployment of the redundant component in the face of failures is also challenging. In this paper, we introduce a novel redundancy strategy, called adaptive standby redundancy (ASR), to achieve resilient performance for discrete manufacturing systems while reducing the cost of employing the duplicated components that are typically used in traditional systems. This novel strategy permits achievement of high levels of utilisation of the system and graceful degradation in case of failure, keeping the system functional. The strategy is then validated in a developed robotic flexible assembly cell (RFAC), which is tested and results on its efficacy and performance enhancement are discussed. [ABSTRACT FROM AUTHOR]

An intelligent system for spatial visual feedback is presented, which enables the robot's autonomy for a range of robotic assembly tasks, in particular for arc welding, in an unstructured and "fixtureless" environment. The robot's autonomy is empowered by an embedded inductive inference-based machine learning module which learns a welded object's structural properties in the form of geometrical properties. In particular, the system tries to recognize line segments, using a spatial (three-dimensional) visual sensor in order to autonomously execute the objective task. The innovative result is that the recognition of the geometric primitives is done without a predefined Computer-Aided Design (CAD) model, significantly improving the system's autonomy and robustness. The system is validated on real-world welding tasks. [ABSTRACT FROM AUTHOR]

In modern industrial production, robotic assembly systems play a crucial role. As robots take on more tasks, the need for formal methods arises to define, control, and execute these tasks. This paper introduces a comprehensive approach to designing and generating control code for robotic assembly systems, taking task sequence planning into account. This methodology utilizes Petri nets (PNs) as a formal modeling and synthesis tool for the controller. Initially, the task sequences for assembly operations are represented using PN formalism. Supervisors are then synthesized for task sequence control specifications. Finally, the control code is obtained by the proposed methodology for industrial robots. By implementing this supervisory control structure, real-time control of the robotic assembly system is achieved. Experimental studies were conducted using an assembly cell equipped with an industrial robot. This methodology bridges the gap between the design and implementation of formal controllers for industrial robots. The proposed approach integrates formal methods into robot programming to leverage several advantages, including correctness assurance, complexity handling, improved documentation and clarity, enhanced safety and reliability, property verification, and scalability.

In robotic assembly of flexible flat cables (FFCs), a unique challenge is the inherent difficulty in manipulating such flexible objects compared to their rigid counterparts and the precise estimation of the cable pose. This work proposes a framework that combines object pose estimation using computer-aided design (CAD) models and multiview fusion to perform precise FFC assembly. Our key insight is that a multiview fusion combined with pretrained 6-D pose estimation models offers a more flexible and precise object pose estimation. In a series of experiments involving FFC insertion tasks requiring assembly tolerances down to 0.1 mm, our approach achieves an insertion success rate of 399 out of 400 total attempts. Furthermore, the assembly tasks include the releasing and securing of FFCs from cable connectors, where the system is successful in 200 out of 200 trials. We have also demonstrated the generalization capability of the methodology by successfully completing insertion tasks for common electronic cables like DisplayPort and USB-A, achieving 199 successes in 200 trials. The results not only validate the feasibility of the proposed approach, but also demonstrate its robustness for real-world industrial applications.

In the domain of flexible manufacturing, Deep Reinforcement Learning (DRL) has emerged as a pivotal technology for robotic assembly tasks. Despite advancements in sample efficiency and interaction safety through residual reinforcement learning with initial policies, challenges persist in achieving context generalization amidst stochastic systems characterized by large random errors and variable backgrounds. Addressing these challenges, this study introduces a novel framework that integrates task attention-based multimodal fusion with an adaptive error curriculum within a residual reinforcement learning paradigm. Our approach commences with the formulation of a task attention-based multimodal policy that synergizes task-centric visual, relative pose, and tactile data into a compact, end-to-end model. This model is explicitly designed to enhance context generalization by improving observability, thereby ensuring robustness against stochastic errors and variable backgrounds. The second facet of our framework, curriculum residual learning, introduces an adaptive error curriculum that intelligently modulates the guidance and constraints of a model-based feedback controller. This progression from perfect to significantly imperfect initial policies incrementally enhances policy robustness and learning process stability. Empirical validation demonstrates the capability of our method to efficiently acquire a high-precision policy for assembly tasks with clearances as tight as 0.1 mm and error margins up to 20 mm within a 3.5-hour training window-a feat challenging for existing RL-based methods. The results indicate a substantial reduction in average completion time by 75 % and a 34 % increase in success rate over the classical two-step approach. An ablation study was conducted to assess the contribution of each component within our framework. Real-world task experiments further corroborate the robustness and generalization of our method, achieving over a 90 % success rate in variable contexts. [ABSTRACT FROM AUTHOR]

Estimating the execution time of assembly task sequences of a new geometric model is an essential prerequisite for task allocation and resource planning decisions in smart multi-robotic assembly cells. This paper discusses an optimization-based method to estimate the execution time of a full sequence of assembly tasks, including picking, aligning, and insertion. Task descriptions, joint space trajectories, assembly task-related motions, and process conditions are used as inputs for the method. The required descriptions of assembly tasks are parametrized, and the resulting function is then combined with the process conditions, assembly task-relevant motions, and the capabilities of the resources in the robotic assembly cell to estimate the execution times. The advantage of the method is the possibility of determining the execution time of an assembly task, taking into account the capabilities of the robot, before assigning it to the multi-robot assembly station. The proposed method is demonstrated experimentally by using a CAD model with the information of Fanuc robot CR7iA/L. The method is implemented in MATLAB using AMPL-API and tested. To determine its effectiveness, the outcomes of the proposed method are compared to the values of the 3-D Fanuc Roboguide (RG). Finally, further research steps to improve the accuracy of the total time for the entire assembly sequence are also discussed. [ABSTRACT FROM AUTHOR]

Aeronautical robotic applications use quite large, heavy robots with huge end effectors that are frequently multifunctional. An assembly jig to hold a fuselage panel and two medium-sized six-axis robots fixed on linear axes, referred to as the internal and the external robot with respect to the curvature of the panel, make up the Lean robotized AssemBly and cOntrol of composite aeRostructures (LABOR) work cell. A distributed software architecture is proposed in which individual modules are developed to execute specific subprocesses, each implementing innovative algorithms that solve the main drawbacks of state-of-the-art solutions. Real-time referencing adopts a point-cloud-based strategy to reconstruct and process the part before drilling, avoiding hole positioning errors. Accurate concentric countersink diameters are made possible through the automatic adjustment of the drilling tool with respect to the skin panel, which guarantees its orthogonality, as well as the implementation of process parameter optimization algorithms based on historical results that compensate for the wear of the drilling bits. Automatic sealing and fastening strategies that involve the measurement of the main fastener quality parameters allow for the complete verification of the entire assembly process of each part. Additionally, an advanced multimodal perception system continuously monitors the collaborative workspace to ensure safe human–robot collaboration (HRC) tasks. Through this integrated architecture, LABOR substantially reduces expenses and facilitates maintenance and programming. [ABSTRACT FROM AUTHOR]

Automated industrial Visual Inspection Systems (VIS) are typically customized for specific applications, limiting their flexibility. They are characterized by a demanding setup, high capital investments, and significant knowledge barriers. In this paper, we propose an alternative architecture for the visual inspection of 3D printed parts or complex assemblies using a robotic arm equipped with hand-eye sensors and controllable lighting system. The core of the proposed Flexible Vision Inspection System (FVIS) is the self-extraction of 3D text annotations from STandard for the Exchange of Product model (STEP) AP242 files. The system self-selects and parametrizes the most suitable inspection algorithm, including lighting settings. Additionally, it autonomously performs self-localization, self-referencing of physical products, and self-planning of robot inspection path based on CAD information. This framework, characterized by self-X, cost-effective, non-invasive, and plug-and-play architecture has the potential to disrupt the business model of vision inspection, enabling an as-a-service solution aligned with the next generation of flexible manufacturing. [ABSTRACT FROM AUTHOR]

This study provides a comprehensive overview of the automated assembly process of large-scale metal structures using industrial robots. Our research reveals that the utilization of industrial robots significantly enhances precision, speed, and cost-effectiveness in the assembly process. The main findings suggest that integrating industrial robots in metal structure assembly holds substantial promise for optimizing manufacturing processes and elevating the quality of the final products. Additionally, the research demonstrates that robotic automation in assembly operations can lead to significant improvements in resource utilization and operational consistency. This automation also offers a viable solution to the challenges of manual labor shortages and ensures a higher standard of safety and accuracy in the manufacturing environment. [ABSTRACT FROM AUTHOR]

Featured Application: This work has the capability to estimate the pose of unseen textureless objects, which can find applications in automated assembly processes. For example, it can assist a robotic arm in assembly or docking tasks by determining the relative spatial poses of multiple objects. Additionally, this work has potential applications in augmented reality tasks, such as estimating the pose of a mold to enable coloring or overlaying visual effects on the mold. The demand for object pose estimation is steadily increasing, and deep learning has propelled the advancement of this field. However, the majority of research endeavors face challenges in their applicability to industrial production. This is primarily due to the high cost of annotating 3D data, which places higher demands on the generalization capabilities of neural network models. Additionally, existing methods struggle to handle the abundance of textureless objects commonly found in industrial settings. Finally, there is a strong demand for real-time processing capabilities in industrial production processes. Therefore, in this study, we introduced a dual-channel Siamese framework to address these challenges in industrial applications. The architecture employs a Siamese structure for template matching, enabling it to learn the matching capability between the templates constructed from high-fidelity simulated data and real-world scenes. This capacity satisfies the requirements for generalization to unseen objects. Building upon this, we utilized two feature extraction channels to separately process RGB and depth information, addressing the limited feature issue associated with textureless objects. Through our experiments, we demonstrated that this architecture effectively estimates the three-dimensional pose of objects, achieving a 6.0% to 10.9% improvement compared to the state-of-the-art methods, while exhibiting robust generalization and real-time processing capabilities. [ABSTRACT FROM AUTHOR]

An effective Augmented Reality and Virtual Reality paradigm is proposed to facilitate introductory robotics course in the first-year engineering curriculum. The AR/VR Application utilization and its impact on the students' learning with respect to robotic assembly and robotic application programming is emphasized in this article. The paper delves into a comprehensive review of the related works presented in the literature. The requirements for the physical assembly and virtual assembly of movable robots are meticulously highlighted. To facilitate course learning a robotic workshop involving steps introduction to robotics, and practical experience on the robot is conducted. The delivery of the course content is made much more effective by inculcating the Virtual experience of the Robotic assembly process. The virtual robotic assembly and manual physical robotic assembly process processes have their own uniqueness and importance and it is left to the students to pick them on a priority basis. Finally, the effectiveness of the proposed course is determined by conducting an online quiz, collecting student feedback, tabulating and analyzing the results. The results demonstrate the effectiveness of the proposed method in creating interest in robotics and related courses among first-year engineering students. [ABSTRACT FROM AUTHOR]

Construction sites often involve the manual transportation of heavy objects, posing risks to workers' safety and efficiency. In this paper, it was proposed a design, development, and evaluation of a service robot specifically created for carrying heavy objects in the construction field. The robot is equipped with robust locomotion capabilities, intelligent perception systems, and efficient control mechanisms to navigate through complex environments and handle various types of loads. It was presented the technical design of the robot, including its hardware components, sensing modalities, and software architecture. Furthermore, it was discussed the experimental validation of the robot's performance in real-world construction scenarios, highlighting its effectiveness in improving productivity, reducing labor costs, and enhancing workplace safety. Through this research, the aim is to demonstrate the potential of service robots as valuable assets in the construction industry, paving the way for future advancements in robotic assistance technologies. [ABSTRACT FROM AUTHOR]

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.

Robotic systems are crucial in modern manufacturing. Complex assembly tasks require the collaboration of multiple robots. Their orchestration is challenging due to tight tolerances and precision requirements. In this work, we set up two Franka Panda robots performing a peg-in-hole insertion task of 1 mm clearance. We structure the control system hierarchically, planning the robots’ feedback-based trajectories with a central policy trained with reinforcement learning. These trajectories are executed by a low-level impedance controller on each robot. To enhance training convergence, we use reverse curriculum learning, novel for such a two-armed control task, iteratively structured with a minimum requirements and fine-tuning phase. We incorporate domain randomization, varying initial joint configurations of the task for generalization of the applicability. After training, we test the system in a simulation, discovering the impact of curriculum parameters on the emerging process time and its variance. Finally, we transfer the trained model to the real-world, resulting in a small decrease in task duration. Comparing our approach to classical path planning and control shows a decrease in process time, but higher robustness towards calibration errors.