CS Events Monthly View
Qualifying ExamCyber-Physical Systems for Logistics Delivery |
|
||
Monday, May 15, 2023, 11:00am - 01:00pm |
|||
The popularity of the e-commerce has promoted the rapid development of the logistics industry in recent years. As an important step in logistics, last-mile delivery from delivery stations to customers’ addresses is now mainly finished by couriers. How to measure the courier’s workload for last-mile delivery and design efficient delivery schemes are crucial for logistics platforms. As a result, we first design, implement, and deploy a nationwide homogeneous order grouping system called FHOG for improving the accuracy of homogeneous order grouping in last-mile delivery for fair courier’s workload assessment. FHOG is deployed in one of the largest logistics companies and the evaluation results show FHOG performs better than the state-of-the-practice. The last-mile delivery process may repeat several times a day if orders arrive at delivery stations in batches, leading to low delivery efficiency. We then design a data-driven relay courier scheduling system, RCS, to reduce the courier idle time and improve the efficiency, which includes: 1) a delivery courier’s mobility prediction model; and 2) an attention-based sequence-to-sequence route generation model. Evaluation results with real-world data show that RCS reduces average relay order delivery time effectively compared with state-of-the-art methods.
Speaker: Wenjun Lyu
Location : CoRE 305
Committee:
Professor Desheng Zhang (Advisor)
Professor Hao Wang
Professor Dong Deng
Professor Xiong Fan
Event Type: Qualifying Exam
Abstract: See above
Organization:
Rutgers University
School of Arts & Sciences
Department of Computer Science
Contact Professor Desheng Zhang