Robotic Disassembly Research Articles

Robotic Disassembly Task Training and Skill Transfer Using Reinforcement Learning

This paper proposes a platform for robots to learn disassembly tasks based on reinforcement learning (RL) techniques. The platform is demonstrated by a robot learning the skill of removing a bolt along a door-chain groove in a data-driven way, where the clearance between the bolt and the groove is less than 1mm. Furthermore, the relationship between the performance of the learned skills and the precision of the robot is studied with a method to control the robot's precision by adding uncorrelated zero-mean Gaussian noise to the robot's actions. Finally, the transferability of the learned skills among robots with different precisions is empirically studied. It has been found that skills learned by a low-precision robot can perform better on a robot with higher precision, and skills learned by a high-precision robot have worse performance on robots with lower precision.

Learning by doing: A dual-loop implementation architecture of deep active learning and human-machine collaboration for smart robot vision

To develop vision systems for autonomous robotic disassembly, this paper presents a dual-loop implementation architecture that enables a robot vision system to learn from human vision in disassembly tasks. The architecture leverages human visual knowledge through a collaborative scheme named ‘learning-by-doing’. In the dual-loop implementation architecture, a human-robot collaborative disassembly loop containing autonomous perception, human-robot interaction and autonomous execution processes is established to address perceptual challenges in disassembly tasks by introducing human operators wearing augmented reality (AR) glasses, while a deep active learning loop is designed to use human visual knowledge to develop robot vision through autonomous perception, human-robot interaction and model learning processes. Considering uncertainties in the conditions of products at the end of their service life, an objective ‘informativeness’ matrix integrating the label information and regional information is designed for autonomous perception, and AR technology is utilised to improve the operational accuracy and efficiency of the human-robot interaction process. By sharing the autonomous perception and human-robot interaction processes, the two loops are simultaneously executed. To validate the capability of the proposed architecture, a screw removal task was studied. The experiments demonstrated the capability to accomplish challenging perceptual tasks and develop the perceptual ability of robots accurately, stably, and efficiently in disassembly processes. The results highlight the potential of learning by doing in developing robot vision towards autonomous robotic disassembly through collaborative human-machine vision systems.

Enhancing Disassembly Practices for Electric Vehicle Battery Packs: A Narrative Comprehensive Review

In the context of current societal challenges, such as climate neutrality, industry digitization, and circular economy, this paper addresses the importance of improving recycling practices for electric vehicle (EV) battery packs, with a specific focus on lithium–ion batteries (LIBs). To achieve this, the paper conducts a systematic review (using Google Scholar, Scopus, and Web of Science as search engines), considering the last 10 years, to examine existing recycling methods, robotic/collaborative disassembly cells, and associated control techniques. The aim is to provide a comprehensive and detailed review that can serve as a valuable resource for future research in the industrial domain. By analyzing the current state of the field, this review identifies emerging needs and challenges that need to be addressed for the successful implementation of automatic robotic disassembly cells for end-of-life (EOL) electronic products, such as EV LIBs. The findings presented in this paper enhance our understanding of recycling practices and lay the groundwork for more precise research directions in this important area.

Human-robot interaction for extraction of robotic disassembly information

ABSTRACT Disassembly of end-of-use products is critical to the economic feasibility of circular feedstock, reusing, recycling and remanufacturing loops. High-volume disassembly operations are constrained by disassembly complexity and product variability. The capability to buffer against timing, quantity and quality uncertainties of end-of-use products impacts the efficiency and profitability of demanufacturing systems. To achieve a competitive operation in the manufacturing life-cycle, disassembly systems need automated lines, however, the unpredictability of core supply challenges automation adaptability. Disassembly robot trajectories that are programmed manually or controlled by vision systems can be time intensive and subject to variability in lighting conditions and image recognition models. Alternatively, this paper presents a novel human-robot disassembly framework to systematically extract and generate robot trajectories derived from human-collaborative robot (cobot) disassembly. The collaborative training station proposed classifies trajectory segments and then adjusts trajectories to station-specific robots in a high-volume disassembly line. Virtual and physical collaborative disassembly case studies are presented and discussed. Results demonstrate the effectiveness of the disassembly data extraction method but indicate a disparity between the expected and ideal disassembly trajectories due to variability from human handling, which is further discussed in this paper.

Towards reuse and recycling of lithium-ion batteries: tele-robotics for disassembly of electric vehicle batteries.

Disassembly of electric vehicle batteries is a critical stage in recovery, recycling and re-use of high-value battery materials, but is complicated by limited standardisation, design complexity, compounded by uncertainty and safety issues from varying end-of-life condition. Telerobotics presents an avenue for semi-autonomous robotic disassembly that addresses these challenges. However, it is suggested that quality and realism of the user's haptic interactions with the environment is important for precise, contact-rich and safety-critical tasks. To investigate this proposition, we demonstrate the disassembly of a Nissan Leaf 2011 module stack as a basis for a comparative study between a traditional asymmetric haptic-"cobot" master-slave framework and identical master and slave cobots based on task completion time and success rate metrics. We demonstrate across a range of disassembly tasks a time reduction of 22%-57% is achieved using identical cobots, yet this improvement arises chiefly from an expanded workspace and 1:1 positional mapping, and suffers a 10%-30% reduction in first attempt success rate. For unbolting and grasping, the realism of force feedback was comparatively less important than directional information encoded in the interaction, however, 1:1 force mapping strengthened environmental tactile cues for vacuum pick-and-place and contact cutting tasks.

A multiobjective decision-making approach for modelling and planning economically and environmentally sustainable robotic disassembly for remanufacturing

Adopting initiatives to extend the useful life of products or recovering their components for reuse, remanufacturing or recycling is a key issue in the attempt to protect the environment and minimise the demand for natural resources. To contribute to the performance of automated disassembly practices, this paper presents a multiobjective decision-making approach based on the optimisation of three goals in a robotic disassembly cell framework: enhancing the economic performance of the process, reducing energy consumption and mitigating the environmental impact. Two real-use cases are presented as demonstrators, supported by appropriate, updated information from industry. The design model allowed the authors to obtain the best robotic disassembly sequence plan, the correct disassembly direction, the best recovery option for the disassembled components – reuse, remanufacturing, recycling or disposal – and the most appropriate disassembly tools, finding the optimal or near-optimal solution that best balances the three sustainability goals. An Enhanced Discrete Bees Algorithm with a mutation operator was employed to find the solution for the optimisation. Moreover, a multiobjective Bees Algorithm, a Non-dominated Sorting Genetic Algorithm II and a Pareto Envelope-based Selection Algorithm II were adopted to solve the multiobjective optimisation problem using different iteration numbers and population sizes. The results provide insights into robotic disassembly processes, encouraging firms to adopt more automated and sustainable remanufacturing strategies.

Multi-Objective Discrete Brainstorming Optimizer to Solve the Stochastic Multiple-Product Robotic Disassembly Line Balancing Problem Subject to Disassembly Failures

Robots are now widely used in product disassembly lines, which significantly improves end-of-life (EOL) product disassembly efficiency. Most of the current research on disassembly line balancing problems focuses on decomposing one product. More than one product can be disassembled concurrently, which can further improve the efficiency. Moreover, uncertainty such as the depreciation of EOL products, may result in disassembly failure. In this research, a stochastic multi-product robotic disassembly line balancing model is established using an AND/OR graph. It takes the precedence relationship, cycle constraint, and disassembly failure into consideration to maximize the profit and minimize the energy consumption for disassembling multiple products. A Pareto-improved multi-objective brainstorming optimization algorithm combined with stochastic simulation is proposed to solve the problem. Furthermore, by conducting experiments on some real cases and comparing with four state-of-the-art multi-objective optimization algorithms, i.e., the multi-objective discrete gray wolf optimizer, artificial bee colony algorithm, nondominated sorting genetic algorithm II, and multi-objective evolutionary algorithm based on decomposition, this paper validates its excellent performance in solving the concerned problem.

Robotic disassembly sequence planning considering parts failure features

AbstractDisassembly is an important step in remanufacturing products. Robotic disassembly helps to improve disassembly efficiency. However, the end‐of‐life products often have the parts with uncertain quality, which is manifested as wear, fracture, deformation, corrosion, and other failure features. The parts failure features always have impacts on disassembly process. First, the evaluation method of parts failure features is researched, and the quantitative model of parts failure features is constructed using fuzzy models. Then, the disassembly information model is established by considering the influence of different failure degrees on the robotic disassembly process. Afterwards, to generate the optimal disassembly solution, deep reinforcement learning (DRL) is used to solve robotic disassembly sequence planning problem which considers parts failure features. Considering the influence of parts failure features on robotic disassembly time, the states, actions and rewards and environment are designed in DRL. Finally, a case study of the double shaft coupling as a waste product is carried out, and the proposed method is compared with the other methods to verify the effectiveness.

Bi-objective optimization-based multi-criteria decision-making framework for disassembly line balancing and employee assignment problem

PurposeAlthough disassembly balancing lines has been studied for over two decades, there is a gap in the robotic disassembly. Moreover, combination of problem with heterogeneous employee assignment is also lacking. The hazard related with the tasks performed on disassembly lines on workers can be reduced by the use of robots or collaborative robots (cobots) instead of workers. This situation causes an increase in costs. The purpose of the study is to propose a novel version of the problem and to solve this bi-objective (minimizing cost and minimizing hazard simultaneously) problem.Design/methodology/approachThe epsilon constraint method was used to solve the bi-objective model. Entropy-based Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) and Preference Ranking Organization methods for Enrichment Evaluation (PROMETHEE) methods were used to support the decision-maker. In addition, a new criterion called automation rate was proposed. The effects of factors were investigated with full factor experiment design.FindingsThe effects of all factors were found statistically significant on the solution time. The combined effect of the number of tasks and number of workers was also found to be statistically significant.Originality/valueIn this study, for the first time in the literature, a disassembly line balancing and employee assignment model was proposed in the presence of heterogeneous workers, robots and cobots to simultaneously minimize the hazard to the worker and cost.

Artificial Learning for Part Identification in Robotic Disassembly Through Automatic Rule Generation in an Ontology

With the increasing concern for sustainable treatment of waste electrical and electronic equipment (WEEE), methods of robotic disassembly of WEEE to address various challenges of handling end-of-life products has been a trend in research. The main challenge for robotic disassembly is the uncertainties of product structures, models, and conditions. The ability of a robotic disassembly system to learn new product structures and reason about existing knowledge of product structure is vital to addressing this challenge. This paper presents an effective learning framework and demonstrates the system’s ability to learn relevant information for the disassembly of LCD monitors. The learning algorithm uses a database of previous disassembly experience of the product family and analyses it to create rules and relations between the components and disassembly concepts before expanding the generic ontology for future disassembly runs. The results show a significant increase from 11% to 87% in successful part identification of LCD monitors after being trained on past disassembly experience. The proposed method can greatly aid robotic disassembly of any product family. Note to Practitioners—Robotic systems struggle to disassemble electronic waste due to the complexity and uncertainties in end-of-life products and variations in models and parts. An artificially intelligent method is proposed to enable a robotic disassembly system to address these uncertainties. The method uses a computing technique resembling the cognitive reasoning of a human mind in the form of a map of disassembly concepts connected by relationships. Artificial learning by the robotic system occurs by collecting data from previous disassembly runs of a product, analyzing the data, and expanding the map of knowledge with new concepts and relational rules found. The approach is tested on the robotic disassembly system’s ability to identify parts of LCD monitors which possess uncertainties. An improvement from 11% of successful part identification to 87% is found, which demonstrate that learning has taken place. This approach will be implemented in a larger robotic disassembly system and tested with real robotic disassembly runs in the near future.

Intuitive teaching approach for robotic disassembly

Intuitive teaching approach for robotic disassembly

Design of a compliant device for peg-hole separation in robotic disassembly

Disassembly is the first step in the remanufacturing of a product. This paper presents the design of a robot end-of-arm tool for removing a peg from a hole, a common operation in the disassembly of mechanical products. The device is a compliant structure that enables the peg to be pulled out of a closely fitting hole without jamming or wedging. The device is reminiscent of the Remote Centre Compliance (RCC) mechanism used by assembly robots to insert cylindrical pegs into cylindrical holes with small clearances. However, whereas the RCC mechanism has primarily to withstand compressive forces, the proposed compliant device must resist tensile forces because of the nature of disassembly operations. The paper details a finite-element modelling study of peg removal with and without using the compliant structure. The results obtained show that the structure markedly reduces the stresses at the points of contact between the peg and the hole and, consequently, the risk of damage to the components being disassembled.

Automatic Screw Detection and Tool Recommendation System for Robotic Disassembly

Abstract Disassembly is an essential process for the recovery of end-of-life (EOL) electronics in remanufacturing sites. Nevertheless, the process remains labor-intensive due to EOL electronics’ high degree of uncertainty and complexity. The robotic technology can assist in improving disassembly efficiency; however, the characteristics of EOL electronics pose difficulties for robot operation, such as removing small components. For such tasks, detecting small objects is critical for robotic disassembly systems. Screws are widely used as fasteners in ordinary electronic products while having small sizes and varying shapes in a scene. To enable robotic systems to disassemble screws, the location information and the required tools need to be predicted. This paper proposes a computer vision framework for detecting screws and recommending related tools for disassembly. First, a YOLOv4 algorithm is used to detect screw targets in EOL electronic devices and a screw image extraction mechanism is executed based on the position coordinates predicted by YOLOv4. Second, after obtaining the screw images, the EfficientNetv2 algorithm is applied for screw shape classification. In addition to proposing a framework for automatic small-object detection, we explore how to modify the object detection algorithm to improve its performance and discuss the sensitivity of tool recommendations to the detection predictions. A case study of three different types of screws in EOL electronics is used to evaluate the performance of the proposed framework.

Optimisation of robotic disassembly plans using the Bees Algorithm

Remanufacturing is a key component of a circular economy. It enables the reduction of landfill and the preservation of natural resources, therefore benefiting the environment. Disassembly is the first stage in the remanufacturing process, but, so far, has been mostly a manual operation. Transitioning from manual to robotic disassembly is desirable in the Industry 4.0 era. A model for planning the sequence of steps a robot needs to take to dismantle a product is proposed in this study. The model has three objectives: to maximise profits, energy savings and reduction in greenhouse gas emissions. The Bees Algorithm, an algorithm inspired by the foraging behaviour of honey bees, was used to obtain near-optimal plans for disassembling gear pumps. Statistical tests were performed on the results obtained with different optimisation parameters to establish statistical significance. They show that the Bees Algorithm was able to optimise disassembly plans for profits, energy savings and reductions in greenhouse gas emissions. • Optimisation of robotic disassembly plans to maximise profits, energy savings and reduction in greenhouse gas emissions. • Application of the Bees Algorithm to an NP-complete optimisation problem. • Bibliometric literature review of robotic disassembly revealings that the field is understudied.

Disassembly assessment from CAD-based collision evaluation for sequence planning

Disassembly sequence planning is the foundation for disassembly process planning. Furthermore, integrating efficient geometrical disassembly feasibility of non-destructive operations can contribute to designing robotic disassembly and remanufacturing systems. Non-destructive operations increase the chance of repurposing parts with less cost but require collision-free trajectories between components. Thus, generating geometrically feasible disassembly sequences is critical for determining the optimal disassembly sequencing and disassembly trajectories. In this work, geometric collision data has generated to develop the disassembly precedence matrix that provides fundamental information for disassembly planning methods. Current methods often require significant manual resources to locate geometrically feasible sequences for disassembly of products. This paper describes the results of utilizing disassembly collision tests to automatically extract interference data from STEP CAD assembly files to determine feasible disassembly operations. A method to determine a precedence matrix that describes all geometrically feasible disassembly operations for disassembly of a selected part or a whole assembly to its components has been developed and tested. Extracted data from STEP files is used to characterize the spatial properties of a component in an assembly and is the basis for the collision test to determine the geometrically feasible disassembly operations. The precedence matrix also identifies the feasible disassembly directions for each component based on the outcomes of the collision tests.

A self-evolving system for robotic disassembly sequence planning under uncertain interference conditions

• A fuzzification of disassembly sequence planning (FDSP) method is proposed. • FDSP offers the capability for DSP to adapt to failures and re-planing online. • The dual-loop self-evolving framework can cope with uncertain interference conditions. Robotic disassembly sequence planning (DSP) is a research area that looks at the sequence of actions in the disassembly intending to achieve autonomous disassembly with high efficiency and low cost in remanufacturing and recycling applications. A piece of key input information being factored in DSP is the interference condition of a product, i.e., a mathematical representation of the spatial location of components in an assembly, usually in the form of a matrix. An observed challenge in the area is that the interference condition can be uncertain due to variations in the end-of-life conditions, and there is a lack of tools available in DSP under uncertain interference. To address this challenge, this paper proposes a new DSP method that can cope with uncertain interference conditions enabled by the fuzzification of DSP (FDSP) . This new approach in the core is a fuzzy and dynamic modeling method in combination with an iterative re-planning strategy, and FDSP offers the capability for DSP to adapt to failures and self-evolve online. Three products are given to demonstrate FDSP.

Robotic disassembly line balancing and sequencing problem considering energy-saving and high-profit for waste household appliances

Waste household appliances contain hazardous substances and valuable components. The timely disposal of these waste products can avoid environmental pollution and improve the recycling rate of resources. Robotic disassembly can realize efficient and precise disassembly to achieve sustainable and clean production. Reasonable allocation of robots and disassembly tasks is the key to achieving efficient production. Reducing energy consumption and improving profits are the focus of the government and enterprises. The tool replacement of the robot needs to be considered in the actual disassembly process, which increases the difficulty of the problem. This study establishes a multi-objective robotic disassembly line balancing and sequencing model to quantify the problem. The model aims to shorten the disassembly completion time and perform disassembly operations with energy-saving and high-profit. An improved genetic simulated annealing algorithm based on problem characteristics is designed. The superiority of the proposed algorithm is verified by solving 21 benchmarks with the number of tasks ranging from 7 to 148 and comparing with five algorithms. In a disassembly case of waste household appliances represented by a microwave oven, 66 disassembly schemes are obtained for decision makers to choose from different emphases. The results show that these schemes can not only achieve efficient and green disassembling but also obtain higher disassembly profits.

Multi-mechanism-based modified bi-objective Harris Hawks optimization for sustainable robotic disassembly line balancing problems

Due to the increasingly severe resource scarcity and environmental pollution, appropriate recovery of end-of-life (EOL) products has gained significant importance in recent years. The disassembly lines are one of the vital steps during the entire recovery process. However, considering the disadvantages of manual disassembly lines such as high labor cost, low efficiency, and harm to workers’ health, the transition to robotic disassembly lines is underway. Therefore, in this paper, a sustainable robotic disassembly line balancing problem (RDLBP) is proposed to improve the disassembly efficiency (cycle time) and environmental friendliness (total energy consumption) simultaneously. To narrow the gap between theory and practice, uncertain processing time, sequence-based tool changeover, and robots with different efficiencies and energy consumption rates are considered, which requires adding the steps of resequencing the tasks and allocating the most suitable robots within each workstation on the basis of assigning the tasks to workstations as evenly as possible. To solve this problem, the epsilon constraint algorithm is used to obtain the exact solutions for small scale cases and verify the validity of the proposed model. Simultaneously, due to the NP-hard nature, a modified bi-objective Harris Hawks optimization (MBOHHO) algorithm is developed to solve the line balancing problem for the first time, which combines opposition-based learning, differential evolution, and Gaussian mutation mechanisms, and modifies the renewal strategy of two vital parameters based on bioenergy consumption pattern, contributing to improve the diversity and help jump out of local optimum. Finally, computational experiments are performed to evaluate the performance of the MBOHHO algorithm by comparing it with four other outstanding optimization algorithms, and the results reveal its effectiveness and superiority in various metrics.

Robotic Disassembly of Electric Vehicles’ Battery Modules for Recycling

Manual disassembly of the lithium-ion battery (LIB) modules of electric vehicles (EVs) for recycling is time-consuming, expensive, and dangerous for technicians or workers. Dangers associated with high voltage and thermal runaway make a robotic system suitable for the automated or semi-automated disassembly of EV batteries. In this paper, we explore battery disassembly using industrial robots. To understand the disassembly process, human workers were monitored, and the operations were analyzed and broken down into gripping and cutting operations. These operations were selected for automation, and path planning was performed offline. For the gripper, a linear quadratic regulator (LQR) control system was implemented. A system identification method was also implemented in the form of a batch least squares estimator to form the state space representation of the planar linkages used in the control strategy of the gripper. A high-speed rotary cut-off wheel was adapted for the robot to perform precise cutting at various points in the battery module case. The simulation results were used to program an industrial robot for experimental validation. The precision of the rotary cutter allowed for a more direct disassembly method as opposed to the standard manual method. It was shown that the robot was almost twice as fast in cutting but slower in pick and place operations. It has been shown that the best option for disassembly of a LIB pack is a human–robot collaboration, where the robot could make efficient cuts on the battery pack and the technician could quickly sort the battery components and remove connectors or fasteners with which the robot would struggle. This collaboration also reduces the danger encountered by the technician because the risk of shorting battery cells while cutting would be eliminated, but the time efficiency would be significantly improved. This paper demonstrates that a robot offers both safety and time improvements to the current manual disassembly process for EV LIBs.

Structural rigidity theory applied to the scaffold-free (dis)assembly of space frames using cooperative robotics

This paper presents a fabrication-informed design method for triangulated space frame structures that remain stable during all phases of their robotic assembly and disassembly without requiring external scaffolding. A graph theoretic framework, based on rigidity theory, is developed to allow the structure, its support conditions, and the impact of robotic support constraints to be simultaneously represented in a single topological framework. The structural system is sequentially designed with an assembly logic based on Henneberg graph-construction steps, which are executed with two robots through a cooperative rigidity-preserving sequence. Ensuring planarity of the resulting graph during these construction steps is shown to lead to intrinsic disassembly potentials within the system. A graph-based algorithm is presented to locate, isolate and remove locally rigid tetrahedral cells formed in the structural system. This algorithm is then utilized to compute a rigidity-preserving robotic disassembly sequence. The design method is demonstrated in the case study design of a wooden space frame arch structure that is robotically (dis)assembled.