Project

# Title Team Members TA Documents Sponsor
25 Semantic Communications for Unmanned Aerial Vehicles
 Chang Su
Chenhao Li
Tianze Du
YU Liu
 Xiaoyue Li design_document2.pdf
final_paper1.pdf
final_paper2.pdf
proposal2.pdf
 Meng Zhang
#TEAM MEMBERS:
1. Yu LIU (yul9),
2. Chenhao LI (cl89),
3. Chang SU (changsu4),
4. Tianze DU (tianzed2)

#TITLE OF THE PROJECT:

Semantic Communications for Unmanned Aerial Vehicles

#Problem & Motivation:

Most existing techniques in semantic communications heavily rely on the direct transmission of each entire image between transmitters and receivers, whose performance is bottlenecked by the transmission procedure rather than the algorithms of semantic understanding. Therefore, we aim to develop a technique for unmanned aerial vehicles (UAVs), which can understand image samples, extract specific semantics, and communicate its symbolic representations to a target receiver (e.g., another UAV or smart device). We anticipate that this technique can be much speedier than the direct transmission of each entire image.

#Solution Overview:

Our design at a high level:
Extract the semantic features of images taken by the camera on UAV, and encode these features into bits for transmission. Bits are transmitted through physical channel. The receivers’decoders understand and infer the messages.

#Solution Components:
- Subsystem 1: Mutual Communication System (MCS) between UAVs and smart devices. The UAV needs to transmit semantic information to receivers. It needs Channel Encoder, Physical Channel and Channel Decoder.
- Subsystem 2: Lighting Semantic Extraction Systems (LSES) for semantic information extraction on UAV. The system needs to understand images information, for example number of people and their locations on images, or other extract useful information.
- Subsystem 3: UAV mechanical, balance and dynamic System (UAVS). We need to modify a “stupid” UAV and make it successfully carry a camera and a microcomputer (e.g.,smartphone), moved around, and take image samples.

#Criterion for success
- Basic Requirements
1. Develop a UAV drone able to carry a camera and a microcomputer (e.g.,smartphone), moved around, and take image samples.
2. The UAV understands its images, especially number of people and their locations on images.
3. The UAV transmits semantic information to receivers.
- Additional Features
1. Successful performance improvements in terms of transmission speed and other important metrics.
2. The UAV may understand other extract useful information (semantics) and their relative locations.

#Distribution of Work
1. Yu Liu: In charge of the whole project. Assist with Lighting Semantic Extraction Systems (LSES) and Mutual Communication System (MCS).
2. Chang Su: In charge of Lighting Semantic Extraction Systems (LSES). Assist with UAV mechanical, balance and dynamic System (UAVS).
3. Chenhao Li: In charge of Mutual Communication System (MCS), Assist with Lighting Semantic Extraction Systems (LSES).
4. Tianze Du: In charge of UAV mechanical, balance and dynamic System (UAVS). Assist with Mutual Communication System (MCS).

A crowd-sourcing urban air quality monitoring system with bikes

Kaiwen Hong, Zhengxin Jiang, Haofan Lu, Haoqiang Zhu

Featured Project

**Problem**

For public bike users, someone may concern about the air quality in which they are currently riding, as well as the places they are going to. However, currently there is no such an air quality monitoring system which provides air quality information in specific areas inside a city such as Haining.

**Solution Overview**

The idea is to apply air quality monitoring devices on the public bike system. The public bike system in Haining is a perfect carrier for IoT (Internet of Things) devices and urban sensing since it has a large and stable user group and all bikes are managed by official organization which means unified modification on all bikes can be done. A monitoring device integrated on the bike can provide the real-time information that users want to know and share data with other users through a cloud server. A real-time air quality map can be created for users with the contribution from all running bikes.

**Solution Components**

Subsystem 1 – on-bike air quality monitoring device. The subsystem is a stm32 microcontroller based design, integrated with air contaminant sensor, speed meter and data transmission modules. Once connected to a smartphone, the subsystem will keep transmitting real-time data to the smartphone.

Subsystem 2 – Software include a user interface and a server. The user interface can be either an app or a website on smartphone. The user interface receives sensor data from the hardware subsystem, displays the real-time statistics, uploads sensor data to server and receives the air quality map from server. The server processes data from all running bikes, creates a real-time air quality map and returns it back to users.

**Criterion for Success**

1. Success of data collection: stable real-time statistic display on user interface, stable data collection on server.

2. Air quality visualization: The air quality map correctly reflects the air quality in Haining city. For example, the concentration of air contamination should be higher in heavy traffic than in intl campus.

3. Speed control: The on-bike device or smartphone should give an alert when the monitored speed exceeds the upper limit or the user set range. This is not the core function of our design, but we add it as we think the function makes sense for safety purpose.