Task allocation and planning for product disassembly with human–robot collaboration

Lee, Meng-Lun; Behdad, Sara; Liang, Xiao; Zheng, Minghui

doi:10.1016/j.rcim.2021.102306

Cited by 75 publications

(16 citation statements)

References 230 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, a solution to the MATA problem for large-scale industrial tasks in mixed human-robot teams remains NP-hard with exponential complexity [22]. Examples of such formulation, which take inspiration from real-time processor scheduling techniques [15], [20], [23], aim to minimize the overall task completion time. Nevertheless, in human-populated environments, optimally assigning tasks using only task duration as a metric is not sufficient, and often it is necessary to deviate from the original plan.…”

Section: A Related Workmentioning

confidence: 99%

A Comprehensive Architecture for Dynamic Role Allocation and Collaborative Task Planning in Mixed Human-Robot Teams

Lamon¹,

Fusaro²,

Momi³

et al. 2023

Preprint

View full text Add to dashboard Cite

The growing deployment of human-robot collaborative processes in several industrial applications, such as handling, welding, and assembly, unfolds the pursuit of systems which are able to manage large heterogeneous teams and, at the same time, monitor the execution of complex tasks. In this paper, we present a novel architecture for dynamic role allocation and collaborative task planning in a mixed human-robot team of arbitrary size. The architecture capitalizes on a centralized reactive and modular task-agnostic planning method based on Behavior Trees (BTs), in charge of actions scheduling, while the allocation problem is formulated through a Mixed-Integer Linear Program (MILP), that assigns dynamically individual roles or collaborations to the agents of the team. Different metrics used as MILP cost allow the architecture to favor various aspects of the collaboration (e.g. makespan, ergonomics, human preferences). Human preference are identified through a negotiation phase, in which, an human agent can accept/refuse to execute the assigned task. In addition, bilateral communication between humans and the system is achieved through an Augmented Reality (AR) custom user interface that provides intuitive functionalities to assist and coordinate workers in different action phases. The computational complexity of the proposed methodology outperforms literature approaches in industrial sized jobs and teams (problems up to 50 actions and 20 agents in the team with collaborations are solved within 1 s). The different allocated roles, as the cost functions change, highlights the flexibility of the architecture to several production requirements. Finally, the subjective evaluation demonstrating the high usability level and the suitability for the targeted scenario.

show abstract

Section: A Related Workmentioning

confidence: 99%

A Comprehensive Architecture for Dynamic Role Allocation and Collaborative Task Planning in Mixed Human-Robot Teams

Lamon¹,

Fusaro²,

Momi³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Within a manufacturing operation, sub-processes can be instinctively allocated to the cobot or the human, based on considerations such as suitability, capability, or human preference. To increase efficiency in a collaborative production environment, a systematic resolution process must be applied to determine which tasks should be conducted by the cobot and which tasks would be best left to a human [50,51]. The individual skillsets of both the cobot and human involved are considered.…”

Section: Task Allocation In Human-robot Collaborationmentioning

confidence: 99%

Task Complexity and the Skills Dilemma in the Programming and Control of Collaborative Robots for Manufacturing

et al. 2023

View full text Add to dashboard Cite

While traditional industrial robots participate in repetitive manufacturing processes from behind caged safety enclosures, collaborative robots (cobots) offer a highly flexible and human-interactive solution to manufacturing automation. Rather than operating from within cages, safety features such as force and proximity sensors and programmed protection zones allow cobots to work safely, close to human workers. Cobots can be configured to either stop or slow their motion if they come in contact with a human or obstacle or enter a protection zone, which may be a high pedestrian traffic area. In this way, a task can be divided into sub-processes allocated to the cobot or the human based on suitability, capability or human preference. The flexible nature of the cobot makes it ideal for low-volume, ‘just-in-time’ manufacturing; however, this requires frequent reprogramming of the cobot to adapt to the dynamic processes. This paper reviews relevant cobot programming and control methods currently used in the manufacturing industry and alternative solutions proposed in the literature published from 2018 to 2023. The paper aims to (1) study the features and characteristics of existing cobot programming and control methods and those proposed in the literature, (2) compare the complexity of the task that the cobot is to perform with the skills needed to program it, (3) determine who is the ideal person to perform the programming role, and (4) assess whether the cobot programming and control methods are suited to that person’s skillset or if another solution is needed. The study is presented as a guide for potential adopters of cobots for manufacturing and a reference for further research.

show abstract

“…The total task time with the three different methods is evaluated with an additional experiment and an arbitrarily selected task for the human, which considered the same task execution instructions in all three cases. More in detail, the motion of the human is designed so as to cyclically intrude in the robot workspace, while the robot performs a random motion with a nominal duration of 30 s. The experimental results of this example test report a total task time equal to 37.80 s for Approach (1), 51.45 s for Approach (2), and 96.31 s for Approach (3). The proposed approach allows us to achieve a percentage improvement of 26.53% with respect to Approach (2), and of 60.75% if Approach (3) is considered as the reference.…”

Section: T-time R-idle C-act-ws R-stopsmentioning

confidence: 99%

“…This paradigm allows a manipulator to work side-by-side with a human operator and to realize a safe sharing of workspace during manufacturing activities. The need of collaborative robotics application in modern manufacturing is driven by the request of flexibility of tasks and automation settings, and of rapidly variable productivity in lot sizes and time to market [2,3]. Furthermore, the introduction of collaborative robotics can reduce the incidence of occupational risks among the employees, and thus increase their working conditions, while enhancing the performance of the production line [4].…”

Section: Introductionmentioning

confidence: 99%

Enhancing fluency and productivity in human-robot collaboration through online scaling of dynamic safety zones

Scalera

Giusti

Vidoni

et al. 2022

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Industrial collaborative robotics is promising for manufacturing activities where the presence of a robot alongside a human operator can improve operator’s working conditions, flexibility, and productivity. A collaborative robotic application has to guarantee not only safety of the human operator, but also fluency in the collaboration, as well as performance in terms of productivity and task time. In this paper, we present an approach to enhance fluency and productivity in human-robot collaboration through online scaling of dynamic safety zones. A supervisory controller runs online safety checks between bounding volumes enclosing robot and human to identify possible collision dangers. To optimize the sizes of safety zones enclosing the manipulator, the method minimizes the time of potential stop trajectories considering the robot dynamics and its torque constraints, and leverages the directed speed of the robot parts with respect to the human. Simulations and experimental tests on a seven-degree-of-freedom robotic arm verify the effectiveness of the proposed approach, and collaborative fluency metrics show the benefits of the method with respect to existing approaches.

show abstract

Task allocation and planning for product disassembly with human–robot collaboration

Cited by 75 publications

References 230 publications

A Comprehensive Architecture for Dynamic Role Allocation and Collaborative Task Planning in Mixed Human-Robot Teams

A Comprehensive Architecture for Dynamic Role Allocation and Collaborative Task Planning in Mixed Human-Robot Teams

Task Complexity and the Skills Dilemma in the Programming and Control of Collaborative Robots for Manufacturing

Enhancing fluency and productivity in human-robot collaboration through online scaling of dynamic safety zones

Contact Info

Product

Resources

About