Robot-based Assembly Research Articles

Robot-Enabled Construction Assembly with Automated Sequence Planning Based on ChatGPT: RoboGPT

Robot-based assembly in construction has emerged as a promising solution to address numerous challenges such as increasing costs, labor shortages, and the demand for safe and efficient construction processes. One of the main obstacles in realizing the full potential of these robotic systems is the need for effective and efficient sequence planning for construction tasks. Current approaches, including mathematical and heuristic techniques or machine learning methods, face limitations in their adaptability and scalability to dynamic construction environments. To expand the current robot system’s sequential understanding ability, this paper introduces RoboGPT, a novel system that leverages the advanced reasoning capabilities of ChatGPT, a large language model, for automated sequence planning in robot-based assembly applied to construction tasks. The proposed system adapts ChatGPT for construction sequence planning and demonstrates its feasibility and effectiveness through experimental evaluation including two case studies and 80 trials involving real construction tasks. The results show that RoboGPT-driven robots can handle complex construction operations and adapt to changes on the fly. This paper contributes to the ongoing efforts to enhance the capabilities and performance of robot-based assembly systems in the construction industry, and it paves the way for further integration of large language model technologies in the field of construction robotics.

Automatic Gripper-Finger Design, Production, and Application: Toward Fast and Cost-Effective Small-Batch Production

Tactile robot-based assembly line adaptation of new products is still limited by the manual redesign, manufacturing, and exchange of the end-effector setup since the gripper fingers must often be adapted to the geometry of the product components to ensure a successful assembly process. In this article we present an automatic finger design, production, and evaluation pipeline, developed to improve this adaptation process. Two different form-closure–based design principles have been implemented to automatically generate the fingertip geometry: a projected surface representation-based approach as well as a Bézier surface fitting strategy. The resulting fingertips are printed via an automatic production unit and experimentally evaluated based on pick and insertion tasks for three different manipulation objects. To illustrate the potential usage of the introduced design methods for machine learning-based fingertip design approaches, we set up the training and testing process for a neural network-based design method. The proposed automatic fingertip design, production, and application framework represent a step further toward small-batch–size production, since the assembly adaptation effort, flexibility, and scalability are significantly improved.

Extension of Established Modern Physics Simulation for the Training of Robotic Electrical Cabinet Assembly

High-performance physics simulation environments are an excellent option to simulate robot-based assembly processes for training faster-than-real-time and providing the necessary data. However, since established physics engines are rigid multi-body simulators at their core, they cannot simulate the deformation process during the assembly of control cabinet terminals. Thus, appropriate extensions of the simulation are necessary. This paper introduces and evaluates extensions incorporating physical joining models to simulate the snap-fit assembly in electrical cabinets. The presented results showed that the extensions can provide input data of high accuracy for the joining models. In this way, they empower the generation of valid training data for snap-fit assembly from standard rigid body simulations.

Reinforcement learning for robotic assembly of fuel cell turbocharger parts with tight tolerances

The efficiency of a fuel cell is not only dependent on the stack, but also to a large extent on the turbocharger, which is responsible for providing the required airflow. Since the individual components, especially those of the rotor, are subject to high demands on manufacturing accuracy, it is crucial to ensure a precise and robust assembly. In order to achieve a scalable assembly process, this paper presents a method for a robot-based assembly of the rotationally symmetric components of the rotor. The assembly task has been reduced to the two essential problems: search and insertion. On this basis, a system was developed, which is able to learn the joining process independently and compensate for positioning inaccuracies with the help of reinforcement learning in combination with a position-controlled robot. The applied reinforcement learning strategy is based on the measurement data of a 6-axis force/torque sensor, with which the current contact state can be evaluated and a decision for the next step can be made. The experimental verification shows that an automation of the assembly process is possible with the proposed strategy. The robot is able to perform the search operation successfully, whereas limitations to the achievable accuracies of the insertion process could be found.

Tolerance management in robot-based assembly optimizes product, process and system deviations

Deviations of individual parts, assemblies, modules, processes, and equipment interact in assembly and can lead to rework or rejects of the finished product. In general, deviations cannot be avoided but must be managed. There are many analysis methods, however only few abstract methods concentrate on optimization. Thus, there is a lack of concrete, easy and feasible optimization methods for deviation reduction. This paper presents a novel method for assembly optimization by combining tolerance chains and a developed optimization tree, which gives a holistic overview of practical improvement measures. The method is validated on an automated robot process in engine production.

Recent advances in hybrid evolutionary algorithms for multiobjective manufacturing scheduling

In real manufacturing systems there are many combinatorial optimization problems (COP) imposing on more complex issues with multiple objectives. However it is very difficult for solving the intractable COP problems by the traditional approaches because of NP-hard problems. For developing effective and efficient algorithms that are in a sense “good,” i.e., whose computational time is small as within 3min, we have to consider three issues: quality of solution, computational time and effectiveness of the nondominated solutions for multiobjective optimization problem (MOP).In this paper, we focus on recent hybrid evolutionary algorithms (HEA) to solve a variety of single or multiobjective scheduling problems in manufacturing systems to get a best solution with a smaller computational time. Firstly we summarize multiobjective hybrid genetic algorithm (Mo-HGA) and hybrid sampling strategy-based multiobjective evolutionary algorithm (HSS-MoEA) and then propose HSS-MoEA combining with differential evolution (HSS-MoEA-DE). We also demonstrate those hybrid evolutionary algorithms to bicriteria automatic guided vehicle (B-AGV) dispatching problem, robot-based assembly line balancing problem (R-ALB), bicriteria flowshop scheduling problem (B-FSP), multiobjective scheduling problem in thin-film transistor-liquid crystal display (TFT-LCD) module assembly and bicriteria process planning and scheduling (B-PPS) problem. Also we demonstrate their effectiveness of the proposed hybrid evolutionary algorithms by several empirical examples.

Solving peg-in-hole tasks by human demonstration and exception strategies

Purpose – The purpose of this paper is to propose a new algorithm based on programming by demonstration and exception strategies to solve assembly tasks such as peg-in-hole. Design/methodology/approach – Data describing the demonstrated tasks are obtained by kinesthetic guiding. The demonstrated trajectories are transferred to new robot workspaces using three-dimensional (3D) vision. Noise introduced by vision when transferring the task to a new configuration could cause the execution to fail, but such problems are resolved through exception strategies. Findings – This paper demonstrated that the proposed approach combined with exception strategies outperforms traditional approaches for robot-based assembly. Experimental evaluation was carried out on Cranfield Benchmark, which constitutes a standardized assembly task in robotics. This paper also performed statistical evaluation based on experiments carried out on two different robotic platforms. Practical implications – The developed framework can have an important impact for robot assembly processes, which are among the most important applications of industrial robots. Our future plans involve implementation of our framework in a commercially available robot controller. Originality/value – This paper proposes a new approach to the robot assembly based on the Learning by Demonstration (LbD) paradigm. The proposed framework enables to quickly program new assembly tasks without the need for detailed analysis of the geometric and dynamic characteristics of workpieces involved in the assembly task. The algorithm provides an effective disturbance rejection, improved stability and increased overall performance. The proposed exception strategies increase the success rate of the algorithm when the task is transferred to new areas of the workspace, where it is necessary to deal with vision noise and altered dynamic characteristics of the task.

Self-optimizing assembly of laser systems

Laser assembly can be a tedious task if performed manually. Especially if miniaturization of the laser is desired, robot-based assembly can greatly improve quality, performance and throughput, while self-optimization is regarded as a strategy to reduce planning efforts and increase the robustness of the assembly. An automated laser assembly system has been developed together with a concept to increase the autonomy through a multi-agent system control structure. The multi-agent system allows assembly steps like sequence planning, measurement of components and deviations, selection of components, soldering elements onto a carrier plate and active resonator alignment to be handled by the system itself and enables the assembly system to uniquely plan every laser system and execute its assembly within a flexible robot-based assembly cell.

Optimization and Improvement in Robot-Based Assembly Line System by Hybrid Genetic Algorithm

In the real world, there are a lot of scenes from which the product is made by using the robot, which needs different assembly times to perform a given task, because of its capabilities and specialization. For a robotic assembly line balancing (rALB) problem, a set of tasks have to be assigned to stations, and each station needs to select one robot to process the assigned tasks. In this paper, we propose a hybrid genetic algorithm (hGA) for solving this problem. In the hGA, we use new representation method. Advanced genetic operators adapted to the specific chromosome structure and the characteristics of the rALB problem are used. In order to strengthen the search ability, a local search procedure is integrated under the framework the genetic algorithm. Some practical test instances demonstrate the effectiveness and efficiency of the proposed algorithm.

Microrobot based micro-assembly sequence planning with hybrid ant colony algorithm

Robot-based assembly sequence planning plays an important role in product design and has been widely researched in the macro world. But in the micro world, the characteristics of microrobot-based assembly, such as complexity and scaling effects, make the assembly problems much more difficult and seldom researched. In this paper, the microrobot-based micro-assembly sequence planning problem is discussed. The problem is transferred as a combinatorial optimization problem with several matrixes, such as the moving wedge matrix, the microrobot performance matrix, and the sensing matrix. Furthermore, the geometrical and visibility constraints of assembly sequence and evaluation criteria for optimization are given. A particle swarm optimization (PSO) algorithm modified ant colony optimization (ACO) algorithm, called a hybrid PS-ACO, is devised to solve the problem efficiently. The combination of local search and global search of PSO is introduced into the ACO algorithm, which can balance the exploration and exploitation performances of searches. The experimental results have shown that the PS-ACO can solve the micro-assembly sequence planning problem with better convergence performance and optimizing efficiency than basic ACO and GA.

A two-stage assembly process planning tooJ for robot-based flexible assembly systems

Abstract Market forces are increasingly forcing manufacturing companies to reduce both the time to market and the design cycle time for new products. These forces have given rise to a new engineering philosophy in which product design and manufacture take place in parallel. Successful implementation of this philosophy depends on the availability of tools which support CAD/CAM integration in a creative way. This paper proposes the use of computer aided process planning (CAPP) as a two-stage procedure: product/process analysis followed by process planning proper. Product/process analysis involves the application of design for manufacturing and assembly techniques via an effective CAD database interface. A prototype two stage computer-based process planning system for robot-based assembly applications is described.

Economic evaluation of robot-based assembly systems

Abstract Economic justification of the use of industrial robots in general-purpose assembly is often necessary prior to implementation. This can only be achieved by realistic analysis and simulation throughout the design and planning of robot-based assembly systems. This paper describes a research project which aims to develop a kinematic and stochastic simulation model to represent the organization and layout of robot-based assembly systems and to evaluate their respective techno-economics viability. It summarizes the various forms of assembly systems, examines the state-of-art in robotic assembly, and identifies alternative organization of robot-based systems. Existing economic models are reviewed and the important role of a model based on analysis and simulation is emphasized. It also states the objective and boundary of the research programme. The paper is concluded by outlining the design methodology adopted by the model and the techniques used in its implementing.

Robot integration within computer-integrated manufacture

Increasingly robots form part of a complex automation scheme, dictating a requirement for robot control systems which can communicate beyond their local working environment. This paper explains how MAP Version 2·1 broadband local area network interfaces have been used to facilitate robot integration with computer-integrated manufacturing systems and describes integration methodologies which can find widespread application. To illustrate the principles involved a robot-based flexible assembly system has been constructed to assemble and test printed circuit boards. Each machine element of the flexible assembly system has been linked to a MAP backbone through the use of ‘OSI intelligent interfaces’ (or gateways). The interfaces incorporate INI COMMengines and were constructed at Loughborough University to achieve MAP to machine-specific protocol conversion and where appropriate to provide enhanced front-end processing facilities in the locality of machines. The paper also describes the features and use of an...

Espfas — A prototype expert system for technological planning in robot-based flexible assembly systems

This paper describes an application of expert systems to the area of technological planning for robot-based flexible assembly systems. The work described in this paper is part of the research being done in the Republic of Ireland as part of the European Strategic Programme for Research and Development in Information Technology (ESPRIT), Project No. 623. The discussion focuses on the role of technological planning, an explanation of the generative approach to planning, the use of robot-based flexible assembly systems, and the need for a planning procedure within these systems. Following this, a description of the logic of the assembly planning system being developed at the University College Galway (U.C.G.) is given, followed by a review of the knowledge which is encoded in the expert system. The final section details some developments, which have been carried out on the system as a result of two case studies.

A laboratory experiment to teach some concepts on sensor-based robot assembly systems

A laboratory experiment is described that can be performed by electrical engineering graduate students and senior undergraduates. The experiment involves the assembly of a diesel-engine oil pump with an IBM RS-1 robot. The robot is instrumented with a force-sensing gripper and an optical binary sensor to detect parts in the gripper. A GE Optomation binary vision system is also used to monitor the manipulator workspace through a charge-coupled device (CCD) camera mounted on the robot arm. The students are required to program the manipulator and to process the information from the various sensors, which are used to recognize assembly components and to verify assembly operations in real-time. This assembly experiment is designed to familiarize electrical engineering students with the problems which dominate robot-based assembly systems and to demonstrate a number of practical sensor-based motion strategies which can overcome part and robot positional uncertainty found in typical manufacturing environments. These sensor-based motion strategies improve the reliability of a robot assembly system. The sensor-based assembly experiment, the laboratory setup, and the sensor-based motion strategies are discussed in detail.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>