DeepFreight: Deep Reinforcement Learning based Truck Fleet Management

This project aims to develop a novel deep reinforcement-learning-based framework for autonomous freight transportation management.

Description:

Faster delivery of nearly everything is an important problem. Shoppers - whether it comes to a new smartphone, groceries or a sofa - increasingly want their orders to arrive at their doorsteps as soon as they click a button. With shipping costs rising and freight volumes outpacing the supply of available trucks, companies are thinking of radical new initiatives to get their products into customers hands more easily, helping to transform shopping as we know it. Thus, innovations to enable intelligent freight transportation and to drive future growth with new business models are of central importance. This project aims to develop a novel deep reinforcement-learning-based framework for autonomous freight transportation management.

Goals:

The goal is to develop a novel deep reinforcement-learning-based framework for autonomous management of freight transportation systems.

Relevant Technologies:

This project includes both theory and implementation in software. Students will learn the concepts and applications of deep reinforcement learning (subset of machine learning).

Website: 

https://web.ics.purdue.edu/~vaneet/publi_grid.htm

Prerequisites:

The members are expected to know Python, and have completed the programming course.

Meeting Time (Fall 2019):

Tuesday 4:30pm - 5:20 pm