Adaptive Task Planning for Multi-Robot Smart Warehouse

Bolu, Ali; Korçak, Ömer

doi:10.1109/access.2021.3058190

Cited by 68 publications

(27 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The average runtime of DoNe-CPTA is 3 seconds with WMT and 4 seconds with SMT. Additional and detailed information about the executions time can be found in the supplementary material 3 . Again, DoNe-CPTA was superior to a-nCAR in all instances regarding execution time.…”

Section: Execution Timementioning

confidence: 99%

Efficient Task Allocation in Smart Warehouses with Multi-delivery Stations and Heterogeneous Robots

Oliveira¹,

Röning²,

Plentz³

et al. 2022

Preprint

View full text Add to dashboard Cite

The task allocation problem in multi-robot systems (MRTA) is an NPhard problem whose viable solutions are usually found by heuristic algorithms. Considering the increasing need of improvement on logistics, the use of robots for increasing the efficiency of logistics warehouses is becoming a requirement. In a smart warehouse the main tasks consist of employing a fleet of automated picking and mobile robots that coordinate by picking up items from a set of orders from the shelves and dropping them at the delivery stations. Two aspects generally justify multi-robot task allocation complexity: (i) environmental aspects, such as multi-delivery stations and dispersed robots (since they remain in constant motion) and (ii) fleet heterogeneity, where robots' traffic speed and

show abstract

Section: Execution Timementioning

confidence: 99%

Efficient Task Allocation in Smart Warehouses with Multi-delivery Stations and Heterogeneous Robots

Oliveira¹,

Röning²,

Plentz³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…They also propose a model to sequence the shelves' visits to the picking stations. Bolu & Korcak (2021) propose a task planning approach that aims at minimising the number of shelves needed to fulfil a batch of orders. Then, they dynamically adapt the system by selecting tasks for the picking stations and the robots.…”

Section: Scheduling and Task Allocationmentioning

confidence: 99%

Supervised learning and tree search for real-time storage allocation in Robotic Mobile Fulfillment Systems

Rimélé,

Grangier,

Gamache

et al. 2021

Preprint

View full text Add to dashboard Cite

A Robotic Mobile Fulfillment System is a robotised parts-to-picker system that is particularly well-suited for e-commerce warehousing. One distinguishing feature of this type of warehouse is its high storage modularity. Numerous robots are moving shelves simultaneously, and the shelves can be returned to any open location after the picking operation is completed. This work focuses on the real-time storage allocation problem to minimise the travel time of the robots. An efficient -but computationally costly -Monte Carlo Tree Search method is used offline to generate high-quality experience. This experience can be learned by a neural network with a proper coordinates-based features representation. The obtained neural network is used as an action predictor in several new storage policies, either as-is or in rollout and supervised tree search strategies. Resulting performance levels depend on the computing time available at a decision step and are consistently better compared to real-time decision rules from the literature.

show abstract

“…From picking goods to arranging them on the shelves and pallets, all the tasks have to be optimized in a way that constructively improves the flow of the supply chain. Techniques such as adaptive task planning and path planning algorithms have been put into practice in order to manage large autonomous systems with limited resources [22].…”

Section: Introductionmentioning

confidence: 99%

Smart Warehouse Management System: Architecture, Real-Time Implementation and Prototype Design

2022

View full text Add to dashboard Cite

The world has witnessed the digital transformation and Industry 4.0 technologies in the past decade. Nevertheless, there is still a lack of automation and digitalization in certain areas of the manufacturing industry; in particular, warehouse automation often has challenges in design and successful deployment. The effective management of the warehouse and inventory plays a pivotal role in the supply chain and production. In the literature, different architectures of Warehouse Management Systems (WMSs) and automation techniques have been proposed, but most of those have focused only on particular sections of warehouses and have lacked successful deployment. To achieve the goal of process automation, we propose an Internet-of-Things (IoT)-based architecture for real-time warehouse management by dividing the warehouse into multiple domains. Architecture viewpoints were used to present models based on the context diagram, functional view, and operational view specifically catering to the needs of the stakeholders. In addition, we present a generic IoT-based prototype system that enables efficient data collection and transmission in the proposed architecture. Finally, the developed IoT-based solution was deployed in the warehouse of a textile factory for validation testing, and the results are discussed. A comparison of the key performance parameters such as system resilience, efficiency, and latency rate showed the effectiveness of our proposed IoT-based WMS architecture.

show abstract

Adaptive Task Planning for Multi-Robot Smart Warehouse

Abstract: This work is supported by Makhina Robotics, Istanbul, Turkey. Ali Bolu worked as a robotics engineer for developing RMFS in Makhina Robotics.

Cited by 68 publications

References 14 publications

Efficient Task Allocation in Smart Warehouses with Multi-delivery Stations and Heterogeneous Robots

Efficient Task Allocation in Smart Warehouses with Multi-delivery Stations and Heterogeneous Robots

Supervised learning and tree search for real-time storage allocation in Robotic Mobile Fulfillment Systems

Smart Warehouse Management System: Architecture, Real-Time Implementation and Prototype Design

Contact Info

Product

Resources

About