The general assignment problem is a classical NP-hard (non-deterministic polynomial-time) problem. In a warehouse, the constraints on the equipment and the characteristics of consecutive processes make it even more complicated. To overcome the difficulty in calculating the benefit of an assignment and in finding the optimal assignment plan, a simulation-based optimization method is introduced. We first built a simulation model of the warehouse with the object-oriented discrete-event simulation (O2DES) framework, and then implemented a random neighborhood search method utilizing the simulation output. With this method, the throughput and service level of the warehouse can be improved, while keeping the number of workers constant. Numerical results with real data demonstrate the reduction of discrepancy between inbound and outbound service level performance. With a less than $10\%$ reduction in inbound service level, we can achieve an over $30\%$ increase in outbound service level. The proposed decision support tool assists the warehouse manager in dealing with warehouse worker allocation problem under conditions of random daily workload.

Lean is a management paradigm that focuses on respect for people and promises improvement in a company’s performance across sectors and sizes. SMEs, in particular, are a point of interest, considering that their malleability in bureaucracy allows for a more significant margin of continuous improvement application. Several organizational theories have gained advantages from technological innovation, and Lean is no exception. The relationships between Lean and new technologies have been studied throughout the years and gained particular interest in the years when Lean started to be integrated with Industry 4.0 (I4.0) to enhance firms’ performance. This article would like to take that discussion from a different point of view, that of I4.0's impact on proving the importance of implementing Lean in manufacturing companies. Through a mixed-method approach of case study and Simulation, this article will answer the identified research question: "How do Lean tools and their integration impact SMEs’ process performance?" by showing the importance of implementing Lean tools in a non-Lean company. The results show that Simulation can identify the Lean tools that benefit the company’s performance most. Managers could benefit from this study by highlighting which tool or combination to invest in according to the impact on operational performance.

Purpose: Due to high customization, companies, which used to follow the make-to-stock (MTS) strategy, are now adopting the make-to-order (MTO) strategy along with MTS in order to cope with high variability in customer demand. Although lean is quite popular in general, its advantage in MTO-MTS environment is quite rare. Therefore, the purpose of this paper is to show the benefits of lean techniques in this environment.Design/methodology/approach: A popular furniture company in Italy is selected for the longitudinal action research and as a part of the lean project, workload control (WLC) is deployed in the selected company. Data were collected through on-site interviews, potential areas of improvement were identified and then suitable countermeasures were proposed and adopted.Findings: This study reveals that the implementation of lean techniques including WLC in a furniture company reduces the throughput time and improves the inventory turnover.Research limitations/implications: This research is based on a single company. Additional empirical studies can help to refine our proposition.Practical implications: The paper shows the practical implementation of WLC as a part of the lean project in MTO-MTS environment. It provides the practitioners and consultants with the way of implementing lean techniques in companies that are planning to adopt MTO-MTS hybrid strategy.Originality/value: This is the first paper that aims to assess the efficiency of the adaption of WLC based on lean principles in a company using MTO-MTS hybrid strategy. Hence, the results are highly valuable for similar companies, especially when are facing transition situations (e.g. from MTS to MTO-MTS).

We tackle the problem of estimating optical flow from a monocular camera in the context of autonomous driving. We build on the observation that the scene is typically composed of a static background, as well as a relatively small number of traffic participants which move rigidly in 3D. We propose to estimate the traffic participants using instance-level segmentation. For each traffic participant, we use the epipolar constraints that govern each independent motion for faster and more accurate estimation. Our second contribution is a new convolutional net that learns to perform flow matching, and is able to estimate the uncertainty of its matches. This is a core element of our flow estimation pipeline. We demonstrate the effectiveness of our approach in the challenging KITTI 2015 flow benchmark, and show that our approach outperforms published approaches by a large margin.