AI-based dynamic route optimization and driver job recommendation tool

Project Reference :


Institution :

Singapore Management University (SMU)

Principal Investigator :

Prof Lau Hoong Chuin

Technology Readiness :

3 (Experimental proof of concept)

Technology Categories :

Artificial Intelligence and Robotics

Background/Problem Statement

Same-day logistics players are crucial for the growth of eCommerce, particularly in urban areas. With eCommerce platforms facilitating continuous sales from multiple vendors, the logistics challenge has intensified. Logistics operators must pick up items from various decentralized locations and deliver them, handle dynamically generated delivery orders, and optimize order delivery for a win-win scenario among stakeholders (customers, eCommerce platform providers, vendors, logistics providers, and riders). In this industry, route optimization and rider dispatch is essential to increase earning potential for riders and reduce carbon footprint.


  • An advanced AI planning and dynamic route optimization and driver job recommendation tool, which leverages the patented Collaborative Urban Delivery Optimization (CUDO) technology from SMU as its core framework
  • An intuitive and easily implementable hierarchical optimization approach based on multiple strategies for order dispatching, which can dynamically adapt to dispatch orders to vehicles according to the status of orders and by considering the travel distance and overtime.
  • A reinforcement learning algorithm that dynamically decides which jobs should be recommended to which riders.


  1. A hierarchical optimization approach for dynamic pickup and delivery problem with LIFO constraints. (Transportation Research Part E: Logistics and Transportation Review , Volume 175, July 2023)
  2. When Routing Meets Recommendation: Solving Dynamic Order Recommendations Problem in Peer-to-Peer Logistics Platform. (In Lecture Notes in Computer Science Proceedings of International Conference on Computational Logistics (ICCL 2023), September 2023, Berlin, Germany)


  • Pilot implementation by a licensee of this technology indicated 20 percent improvement in efficiency and save 500 hours in delivery time.
  • Experimental studies demonstrate the stability of the hierarchical optimization approach when executed on large-scale real data sets.
  • The result on real-world instances shows that the hierarchical optimization approach outperforms the current practice and has broader applicability.
  • When more companies deploy such technology, they will reap the benefit of operational efficiency, and the riders will benefit from better job recommendations and better income and reduce carbon foot-print.

Potential Application(s)

eCommerce Logistics Sector : Same-day delivery/logistics planner, Route optimization,  Logistics operational efficiency improvement for urban logistics.

We welcome interest from the industry for collaboration/ co-development / customisation of the technology into a new product or service. If you have any enquiries or are keen to collaborate, please contact us.