Simultaneous allocation and sequencing of orders for robotic mobile fulfillment system using reinforcement learning algorithm

Perumaal Subramanian, Saravana; Kumar Chandrasekar, Selva

doi:10.1016/j.eswa.2023.122262

Cited by 4 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, this variable compliance policy demonstrates resilience to various beginning conditions and the ability to generalize to increasingly complicated situations. In order to reduce the distance travelled by mobile robots, the Simultaneous Allocation and Sequencing of Orders Reinforcement Learning (SASORL) technique is suggested in [9]. In contrast to current techniques, the SASORL algorithm simultaneously optimizes sequencing and order allocation, leading to a considerable reduction in the trip distance of mobile robots.…”

Section: Introductionmentioning

confidence: 99%

Generation of robotized assembly order using Liaison and Matrix methods: A comparative study

Dash,

Sahu,

Dash

2024

Preprint

View full text Add to dashboard Cite

A robotic assembly process must be properly developed to achieve the highest throughput, viability, and efficiency. A great variety of ways to order creation have been documented in various literatures, each with its own methodology. However, the majority of literature employs soft computing strategies to generate assembly orders. This paper compares two order generating approaches, the liaison method and the matrix method. The matrix method offers a wide variety of possible applications. This technique may be implemented into the robot motion control software and is also simpler to add into automation operations. This technique has a high degree of convergence and uniqueness. However, the building of matrices must be done properly in order to obtain the correct result. The liaison method employs a logical approach via a series of inquiries that result in the desired precedence connection among the components. Assembly orders are generated using precedence relationships. The success of this strategy is dependent on the responses to a set of questions sent to each liaison. This method's appropriateness is related to items that have fewer components. The two approaches that have been chosen are deliberated about and applied to arbitrarily chosen items, which serve as the basis for the creation of a fundamental and correct approach for the production of robotic assembly orders. The study demonstrates that robotic assembly cells may use the matrix technique. The goal of the ongoing effort is to increase the robotic assembly system's capacity and adaptability.

show abstract

Section: Introductionmentioning

confidence: 99%

Generation of robotized assembly order using Liaison and Matrix methods: A comparative study

Dash,

Sahu,

Dash

2024

Preprint

View full text Add to dashboard Cite

show abstract

An efficient Q-learning integrated multi-objective hyper-heuristic approach for hybrid flow shop scheduling problems with lot streaming

Chen,

Du,

Mumtaz

et al. 2025

Expert Systems with Applications

View full text Add to dashboard Cite

A comparative analysis of constraint and connectivity graph techniques for assembly sequence generation in robotic assembly cells

Dash,

Sahu

2024

Proceedings of the Institution of Mechanical Engineers, Part E:

View full text Add to dashboard Cite

The paper describes a comparative study on the assortment of appropriate assembly-generating techniques for robotic assembly cells. Several techniques have been developed and tested for the creation of viable sequences. Most of these techniques employ computational techniques to generate assembly sequences. Nevertheless, these techniques rely on a large number of assumptions and use insignificant data during the development of assembly sequences. In the present study, two techniques, viz., the connectivity graph technique and the constraint technique are selected, since they are very general, expedient, and easy to implement. Further, selected techniques can easily be automated to increase the productivity of robotics assembly cell. Each technique was applied to four products with different complexities to check their suitability in the context of robotic assembly cell. In the connectivity graph technique, the disassembly of components begins with the sink node in the connectivity graph and ends when no sink node is available. The constraint technique chooses two constraints: the G-constraint and the C-constraint. The process of disassembling the components starts with a component that does not have any G-constraint and satisfies the C-constraint. The G-constraint checks for geometric interference, and the C-constraint checks for connectivity relationships among the components. Both techniques are automated using C++ programming to obtain rapid and efficient results. The automation of assembly techniques is expected to lead to a revolutionary transformation in the assembly sector. The connectivity graph technique is found to be suitable for the robotic assembly cells as described in this article.

show abstract

Simultaneous allocation and sequencing of orders for robotic mobile fulfillment system using reinforcement learning algorithm

Cited by 4 publications

References 34 publications

Generation of robotized assembly order using Liaison and Matrix methods: A comparative study

Generation of robotized assembly order using Liaison and Matrix methods: A comparative study

An efficient Q-learning integrated multi-objective hyper-heuristic approach for hybrid flow shop scheduling problems with lot streaming

A comparative analysis of constraint and connectivity graph techniques for assembly sequence generation in robotic assembly cells

Contact Info

Product

Resources

About