-
Notifications
You must be signed in to change notification settings - Fork 5
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
1 changed file
with
20 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,4 +1,24 @@ | ||
[Dissertation.pdf](https://jyjblrd.github.io/part_II_project_dissertation/Dissertation/dissertation.pdf) | ||
|
||
In this project, I: | ||
1. Design and implement a novel distributed monocular visual SLAM system, capable of | ||
localization, relative pose estimation, and collaborative mapping, all while being tolerant | ||
to degraded network conditions and not reliant on any single leader agent (section 3.2). | ||
2. Evaluate the performance of my system on standard datasets, **demonstrating its su- | ||
perior performance over comparable state-of-the-art systems (section 4.3).** | ||
3. Create a simulation environment for testing and evaluating my system locally (sec- | ||
tion 3.6). | ||
4. Develop a custom collision avoidance framework (section 3.3) and deploy it alongside | ||
my SLAM system on physical robots, **demonstrating the practical use cases of my | ||
system and benchmarking real-world performance (section 4.4).** | ||
5. **Contribute as a co-author to the paper The Cambridge RoboMaster: An Agile | ||
Multi-Robot Research Platform**. My distributed SLAM system is included in | ||
the paper and used to evaluate the robotics platform (section 3.7.1). | ||
6. Develop Multi-Agent EVO – the first open-source evaluation library for multi-agent SLAM | ||
systems (section 3.5). | ||
7. Develop the Raspberry Pi Video Publisher – a performant platform for SLAM data collec- | ||
tion and augmented reality visualizations – and set up a continuous integration and de- | ||
ployment pipeline to automatically deploy the latest builds to the devices (section 3.7.3). | ||
|
||
https://github.com/jyjblrd/distributed_visual_SLAM/assets/40762456/6db2d506-c0fd-4976-94fb-ae1da50cfd12 | ||
|