Beibei97's starred repositories
Courier-Competition-Round1
智慧物流：新冠期间饿了么骑士行为预估比赛第一轮，预测骑手下一步行动
SendyLogisticsChallenge
this challenge aims to predict the estimated time of delivery of orders, from the point of driver pickup to the point of arrival at final destination.
healthcare-logistics
Materials for the modelling healthcare logistics taught component of HPDM097
Sendy-Logistics-Challenge
This is a Sendy Logistics challenge that aims to predict the estimated time of delivery of orders, from the point of driver pickup to the point of arrival at final destination.
Sendy-Logistics-Challenge
This challenge aims to predict the estimated time of delivery of orders, from the point of driver pickup to the point of arrival at final destination.
Beijing-Subway-System
北京地铁导航系统，采用A*算法，输出为时间最短的路线以及票价，内含北京所有地铁站精确的经纬度和全部票价信息
Flood_Tweets
A research internship under the supervision of Dr. Srijith PK, where I helped to develop a tweet classifier for disaster-related tweets that sought to identify if they contained helpful emergency-relief information (e.g., where to find supplies), and further identified , contact information for emergency personnel, if present.
Vehicle-Routing-Problem-VRP-with-Time-Window
The Vehicle Routing Problem with Time Windows (VRPTW) is the extension of the Capacitated Vehicle Routing Problem (CVRP) where the service at each customer must start within an associated time interval, called a time window. Time windows may be hard or soft. In case of hard time windows, a vehicle that arrives too early at a customer must wait until the customer is ready to begin service. In general, waiting before the start of a time window incurs no cost. In the case of soft time windows, every time window can be violated barring a penalty cost. The time windows may be one-sided, e.g., stated as the latest time for delivery. Time windows arise naturally in problems faced by business organizations which work on flexible time schedules. Specific problems with hard time windows include security patrol service, bank deliveries, postal deliveries, industrial refuse collection, grocery delivery, school bus routing, and urban newspaper distribution. Among the soft time window problems, dial-a-ride problems constitute an important example.
route-optimization
Produces optimal routing for freight deliveries, accounting for multiple trucks working in tandem, and multiple dispatch depots.
Package-Delivery
Determine the optimal package delivery route to minimize mileage while meeting user-defined constraints
RouteOptimization
A case study on optimizing on-demand restaurant delivery
Pickup-Delivery-Route-Finder
CMPUT 275 Final Project: Find an the most efficient order route to pickup and deliver multiple orders, a variation of the travelling salesman problem.
drone-delivery-optimal-learning
Simulation of drone-based package delivery to determine best route learning policy
Modelling-and-Analysis-of-a-Vehicle-Routing-Problem-with-Time-Windows-in-Freight-Delivery
A MSc's Dissertation Project which focuses on Vehicle Routing Problem with Time Windows (VRPTW), using both exact method and heuristic approach (General Variable Neighbourhood Search)
Vechicle-Routing-Problem-VRP-with-Pickup-and-Delivery
Pickup-and-Delivery Problems (PDPs) constitute an important family of routing problems in which goods or passengers have to be transported from different origins to different destinations. These problems are usually defined on a graph in which vertices represent origins or destinations for the different entities (or commodities) to be transported. PDPs can be classified into three main categories according to the type of demand and route structure being considered. In many-to-many (M-M) problems, each commodity may have multiple origins and destinations and any location may be the origin or destination of multiple commodities. These problems arise, for example, in the repositioning of inventory between retail stores or in the management of bicycle or car sharing systems. One-tomany- to-one (1-M-1) problems are characterized by the presence of some commodities to be delivered from a depot to many customers and of other commodities to be collected at the customers and transported back to the depot. These have applications, for example, in the distribution of beverages and the collection of empty cans and bottles. They also arise in forward and reverse logistics systems where, in addition to delivering new products, one must plan the collection of used, defective, or obsolete products. Finally, in one-to-one (1-1) problems, each commodity has a single origin and a single destination between which it must be transported. Typical applications of these problems are less than- truckload transportation and urban courier operations.
Inventory-Routing-Problem-IRP-
It can be described as the combination of vehiclerouting and inventory management problems, in which a supplier has to deliver products to a number of geographically dispersed customers, subject to side constraints. It provides integrated logistics solutions by simultaneously optimizing inventory management, vehicle routing, and delivery scheduling. Some exact algorithms and several powerful metaheuristic and matheuristic approaches have been developed for this class of problems, especially in recent years. The purpose of this article is to provide a comprehensive review of this literature, based on a new classification of the problem. We categorize IRPs with respect to their structural variants and the availability of information on customer demand.
genetic-algorithm
With hybrid genetic algorithm to solve the logistics distribution path: from a logistics center with more than one delivery vehicle delivery to multiple customers, each customer's location and the demand for certain goods, each distribution vehicle load must be, the maximum range of the primary distribution is certain, for reasonable arrangement of the vehicle distribution route, to optimize the objective function, and satisfy the following conditions: (1) each distribution path each customer's demand is less than the sum of the distribution of vehicle load; (2) each of the distribution path length is not more than the biggest distance delivery vehicles a distribution; (3) must satisfy each customer's demand, and only by a distribution vehicle delivery. Distribution total mileage to be shortest as objective function
Carton-box-detector-to-help-smother-operations-in-supply-chain
This model will detect carton boxes in a video(like from CCTV camera etc),and count them .This is a application in used during supply chain management and logistics.
LCLPR
in order to solve the optimization problem of logistics distribution system for fresh food, it provides a low‐carbon and environmental protection point of view, based on the characteristics of perishable products, and combines with the overall optimization idea of cold chain logistics distribution network, where the green and low‐carbon location–routing problem (LRP) model in cold chain logistics is developed with the minimum total costs as the objective function, which includes carbon emission costs. A hybrid genetic algorithm with heuristic rules is designed to solve the model.
USFQ-Traffic-in-Ecuador
Research in data analysis, machine learning and mathematical modeling, leading to solve transportation problems across Ecuador, Mexico, and other countries of Latin America. Project lead by University of San Fransicso in Quito, in Cooperation with MIT Center for Transportation and Logistics.
MOVEHACK-DIGITALTWIN2.0
To achieve the concept of Digital Twin to monitor logistics supply chain of network and to bridge the communication gap and form a closed loop of events
Bachelor-Dissertation
LOGISTICS CAPACITY PLANNING OF AIRCRAFT FINAL ASSEMBLY UNDER THE LEARNING CURVE
planning-agent
logistics planning problems for an Air Cargo transport system using a planning search agent.
Group-1-UAV-simulation
A UAV SIMULATION ENGINE FOR LOGISTICS APPLICATIONS IN FUTURE SMART CITIES
AGvehicle_routing_problem
Vehicle routing and dispatching problem used in the agricultural robotics and logistics
drl_binpacking
3D bin packing is a classical and challenging combinatorial optimization problem in logistics and production systems. An effective bin packing algorithm means the reduction of total packing cost and increase in utilization of resources. Because the cost of packing materials, which is mainly determined by their surface area, occupies the most part of packing cost, and in many real business scenarios there is no bin with fixed size, so AI Department of Cainiao proposed a new type of 3D bin packing problem. The objective of this new type of 3D bin packing problem is to pack all items into a bin with minimized surface area. And a DRL method based on the sequence-to-sequence model is proposed to solve the problem. This is the research paper link: https://arxiv.org/abs/1708.05930. Source code of this method can be found in the project.
python_scrapy_express
:beetle:利用Python获取物流运输路线（Use Python to get logistics transportation routes）