The dramatic growth of global e-commerce has led to a surge in demand for efficient and cost-effective order fulfillment which can increase customers' service levels and sellers' competitiveness. However, managing order fulfillment is challenging due to a series of interdependent online sequential decision-making problems. To clear this hurdle, rather than solving the problems separately as attempted in some recent researches, this paper proposes a method based on multi-agent reinforcement learning to integratively solve the series of interconnected problems, encompassing order handling, packing and pickup, storage, order consolidation, and last-mile delivery. In particular, we model the integrated problem as a Markov game, wherein a team of agents learns a joint policy via interacting with a simulated environment. Since no simulated environment supporting the complete order fulfillment problem exists, we devise Order Fulfillment COoperative mUlti-agent Reinforcement learning Scalable Environment (OFCOURSE) in the OpenAI Gym style, which allows reproduction and re-utilization to build customized applications. By constructing the fulfillment system in OFCOURSE, we optimize a joint policy that solves the integrated problem, facilitating sequential order-wise operations across all fulfillment units and minimizing the total cost of fulfilling all orders within the promised time. With OFCOURSE, we also demonstrate that the joint policy learned by multi-agent reinforcement learning outperforms the combination of locally optimal policies.

In particular, we model the integrated problem as a Markov game, wherein a team of agents learns a joint policy via interacting with a simulated environment.

The dramatic growth of global e-commerce has led to a surge in demand for efficient and cost-effective order fulfillment which can increase customers' service levels and sellers' competitiveness. However, managing order fulfillment is challenging due to a series of interdependent online sequential decision-making problems. To clear this hurdle, rather than solving the problems separately as attempted in some recent researches, this paper proposes a method based on multi-agent reinforcement learning to integratively solve the series of interconnected problems, encompassing order handling, packing and pickup, storage, order consolidation, and last-mile delivery. In particular, we model the integrated problem as a Markov game, wherein a team of agents learns a joint policy via interacting with a simulated environment. Since no simulated environment supporting the complete order fulfillment problem exists, we devise Order Fulfillment COoperative mUlti-agent Reinforcement learning Scalable Environment (OFCOURSE) in the OpenAI Gym style, which allows reproduction and re-utilization to build customized applications.

To meet order fulfillment targets, manufacturers seek to optimize production schedules. Machine learning can support this objective by predicting throughput times on production lines given order specifications. However, this is challenging when manufacturers produce customized products because customization often leads to changes in the probability distribution of operational data -- so-called distributional shifts. Distributional shifts can harm the performance of predictive models when deployed to future customer orders with new specifications. The literature provides limited advice on how such distributional shifts can be addressed in operations management. Here, we propose a data-driven approach based on adversarial learning and job shop scheduling, which allows us to account for distributional shifts in manufacturing settings with high degrees of product customization. We empirically validate our proposed approach using real-world data from a job shop production that supplies large metal components to an oil platform construction yard. Across an extensive series of numerical experiments, we find that our adversarial learning approach outperforms common baselines. Overall, this paper shows how production managers can improve their decision-making under distributional shifts.

Locus Robotics has signed what it claims to be one of the largest deployments of autonomous mobile robots (AMRs) ever. GEODIS is a leading global transport and logistics provider and has used Locus' AMRs since 2018, when it first deployed Locus' AMRs at a site in Indiana. The global third-party logistics company (3PL) has currently deployed Locus AMRs at 14 sites around the world, serving a variety of retail and consumer brands, including warehouses in the U.S and Europe. At press time, Locus hadn't provided how many of its AMRs GEODIS will have overall after these 1,000 are deployed. Locus told The Robot Report it doesn't have concrete evidence this is one of the largest AMR deals ever.

Berkshire Grey Inc, the leading AI-enabled robotic solutions, has announced its partnership with North Highland, a worldwide management consulting firm, to solve global supply chain challenges and enhance the throughput of eCommerce fulfillment. With surging demand in the E-Commerce Industry, lack of labor issues, and increasing customer expectations for speed and quality, chief supply chain officers (CSCOs) are under more stress than ever to optimize supply chain operations and enhance supply chain resiliency. Berkshire Grey offers solutions to customers that support order fulfillment over the entire supply chain by providing the most extensive portfolio of (IER) Intelligent Enterprise Robotic solutions available. Berkshire Grey's complete services cover design, installation, testing, and commissioning, as well as ongoing support employing cloud-based AI solutions for auspicious maintenance, system operations management, analytics, and integration. Major retailers and consumer product companies trust North Highland consultants to advise and deliver cutting-edge technology, which is why North Highland chose Berkshire Grey's innovative robotic solutions.

With the increase of order fulfillment options and business objectives taken into consideration in the deciding process, order fulfillment deciding is becoming more and more complex. For example, with the advent of ship from store retailers now have many more fulfillment nodes to consider, and it is now common to take into account many and varied business goals in making fulfillment decisions. With increasing complexity, efficiency of the deciding process can become a real concern. Finding the optimal fulfillment assignments among all possible ones may be too costly to do for every order especially during peak times. In this work, we explore the possibility of exploiting regularity in the fulfillment decision process to reduce the burden on the deciding system. By using data mining we aim to find patterns in past fulfillment decisions that can be used to efficiently predict most likely assignments for future decisions. Essentially, those assignments that can be predicted with high confidence can be used to shortcut, or bypass, the expensive deciding process, or else a set of most likely assignments can be used for shortlisting -- sending a much smaller set of candidates for consideration by the fulfillment deciding system.

The global automation market size is expected to generate $214B by the end of 2021, of which $29B (14%) will come from manufacturing and factory automation. This is because numerous processes in manufacturing are repetitive, rule-based, and can be automated using RPA bots. For instance, bill of materials (BOM), data migration and analytics, invoices, and inventory reporting are highly repetitive and time consuming tasks if done manually. A typical rule-based process can be 70%-80% automated. RPA bots handle rule-based repetitive tasks and minimize the need for human interference.

While most discussions about the application of artificial intelligence (AI) in manufacturing focus on technology in development, AI is not entirely a technology of the future for industry. Real world applications exist and products are available today for industrial use. A key example of AI being put to use in core applications can be found in the evolution of bin picking to order fulfillment picking. In a recent blog post, Sarah Mellish of Yaskawa noted that "traditional bin picking methods have given way to order fulfillment picking approaches, moving the complexity of the process from the hardware to the software. This is important because of the physical modifications required to meet supply chain variability today."