Motion Prediction and Offloading Project
Dnr:
NAISS 2024/22-609
Type:
NAISS Small Compute
Principal Investigator:
Ziyu Zhong
Affiliation:
Lunds universitet
Start Date:
2024-04-29
End Date:
2025-05-01
Primary Classification:
20203: Communication Systems
Webpage:
Allocation
Abstract
Topic: edge computing for AR/VR game.
1. What is the best prediction horizon that can be achieved considering different motion pattern variables using the prediction-based controller?
2. Comparison of prediction performance for different user motion patterns, between deep learning LSTM and control based Kalman filter.
3.How many time do we buy from prediction to reduce M2P latency?