Multi-robot Assisted Wi-Fi Coverage Characterization and Propagation Model Estimation
10:00am
Room 2610 (Lifts 31-32), 2/F Academic Building, HKUST

Thesis Examination Committee

Prof Roger CHENG, ECE/HKUST (Chairperson)
Prof Vincent Lau, ECE/HKUST (Thesis Supervisor)
Prof Ling Shi, ECE/HKUST

 

Abstract

Indoor Wi-Fi propagation model characterization is crucial to Wi-Fi access points deployment. The current method to do the characterization involves frequent human interactions and sample-taking, causing a high labor intensity and low estimation efficiency. We propose to use multiple robot agents to replace humans in the characterization task. We formulate the propagation model parameter estimation problem and the robots path-planning problem into an online Markov Decision Process (MDP) & Maximum Likelihood Estimation (MLE) problem. Online MDP is solved with online value iteration while the near optimal MLE solutions are found with Particle Swarm Optimization tool. Multi-robot platform free workers from intensive labor effort without losing measurement accuracy. The online decision making strategy and parameters estimation allows the Wi-Fi propagation model characterization process to be much faster with equal or better performance.

讲者/ 表演者:
Liyao ZHAO
语言
英文
新增活动
请各校内团体将活动发布至大学活动日历。