Research

Share        

Multi-robot optimization, scheduling and allocation

Objective

To develop a fleet management system for the following two use cases:

  • On demand Mobility

  • Coordination of ground operation at airport


Description

There is considerable interest related to management of a fleet of autonomous vehicles in both academia and industry. In order to approach the goals of the project, various techniques including exact and heuristic methods have been explored to address vehicle routing problem (VRP). In this project, we focus mainly on Dial a Ride Problems, which is a special kind of VRP. A fleet management system has been developed for transportation of passengers between the given origin and destination pairs. Simulation tests indicated that algorithms based on heuristic methods (Ant Colony Optimisation, Tabu Search, etc.) provides feasible and near optimal solution for large scale problems, while delivering comparatively faster computation than that of exact method. Future works include the development of robust algorithms for both static and dynamic routing under different traffic and weather scenarios.


Demonstration Video




Co-Principal Investigators


Associate Prof. Justin Dauwels (NTU)

Telephone: 6790 5410
Office: S2.2-B2-15
Email: jdauwels@ntu.edu.sg
Mr. Paul Tan (STE)

Telephone: 6660 1052
Office: S1-B4a-03
Email: paultan@stengg.com