An AI-Driven Secure and Intelligent Robotic Delivery System
Wang, Wei; Gope, Prosanta; Cheng, Yongqiang
Last-mile delivery has gained much popularity in recent years, it accounts for about half of the whole logistics cost. Unlike container transportation, companies must hire significant number of employees to deliver packages to the customers. Therefore, many companies are studying automated methods such as robotic delivery to complete the delivery work to reduce the cost. It is undeniable that the security issue is a huge challenge in such a system. In this article, we propose an AI-driven robotic delivery system, which consists of two modules. A multilevel cooperative user authentication module for delivering parcel using both PIN code and biometrics verification, i.e., voiceprint and face verification. Another noncooperative user identification module using face verification which detects and verifies the identification of the customer. In this way, the robot can find the correct customer and complete the delivery task automatically. Finally, we implement the proposed system on a Turtlebot3 robot and analyze the performance of the proposed schema. Experimental results show that our proposed system has a high accuracy and can complete the delivery task securely.
Wang, W., Gope, P., & Cheng, Y. (in press). An AI-Driven Secure and Intelligent Robotic Delivery System. IEEE Transactions on Engineering Management, https://doi.org/10.1109/TEM.2022.3142282
|Journal Article Type||Article|
|Acceptance Date||Jan 3, 2022|
|Online Publication Date||Mar 10, 2022|
|Deposit Date||Apr 6, 2022|
|Publicly Available Date||Apr 11, 2022|
|Journal||IEEE Transactions on Engineering Management|
|Publisher||Institute of Electrical and Electronics Engineers|
|Peer Reviewed||Peer Reviewed|
|Keywords||AI; Audio classification; Cooperative user authentication; Face verification; Multilevel authentication; Noncooperative user authentication; Robotic delivery system; Speaker verification|
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
You might also like
Consensus Adversarial Defense Method Based on Augmented Examples