Progress Report 1

Last week I did a lot of writing. This week has been more of a "plan ahead and think back" week. It is time to plan the development of the new system. The most important thing for now is to limit this to a task that can be completed in the limited timeframe of the thesis.

On the writing side of things I have continued my review of existing systems, but also the writing about the fundamental technologies that they rely upon (GPS, WLAN, RFID, computer vision).

One thing to remember is that a location can simply be defined as any kind of "fingerprint" associated with it. This is easy to forget when there are such obvious and intuitive techniques such as GPS. I have seen this done by looking at colour histograms of a scene, or using a multitude of basic sensors to obtain a "fingerprint" of a location. Very interesting.

Navigation Using Stereo Vision with an ER1 Robot

Video description
This video is a short demonstration of Automated Navigation using Grassfire Algorithm on input from Stereo Vision. The ER-1 Robot gets the input from the cameras and the program deduces a bird's eye view of the scenario. It then uses the navigation algorithm to plan a route and executes it.
Final Year Project at University of Plymouth - BEng Robotics and Automated Systems.

Completed Work

Up to this point, the following has been done:
- Introductory writing: background, problems, technical challenges, goal, aim...
- Sample scenarios leading to some criteria--and some properties--a good system should possess. Those criteria will guide the analysis of current systems and will provide a basis for the system to be proposed.
- Phone-based GPS solutions have been evaluated.
- I have gathered resources on other systems as well as underlying technologies. The next stage is to evaluate and explain those.
- Also started to look at practical matters (hardware, programming libraries, etc.)

Resources

On the right hand side of this page you can find a 'Resources' page. I will put anything I come across that is relevant to the project there.

Introduction

The project is about multimodal navigation systems primarily targetting visually impaired people. Others who might benefit are those with memory loss or those getting into situations where they might be temporarily blinded such as fire fighters. Autonomous robot navigation can also benefit.
There are some commercially available GPS systems designed for visually impaired, as well as quite a few research prototypes using anything from GPS and WLAN to cameras and RFID tags. Those modes have been investigated separately, but relatively little has been done to fuse the technologies together to provide a richer and more accurate system that works in other environments than simply outdoors (GPS has this limitation). If we could create a very good multimodal system, the capabilities could extend far beyond simple navigation. Scene description would be enormously helpful for someone who can't use their eyes for that purpose. Other location-based services are possible and would be easy to integrate into such a system.
There are, however, many theoretical and practical issues that needs to be overcome. When information is received from multiple sources, the system needs to be able to judge how to use it and how to present it in an efficient and minimally distracting way. This can depend on both the user's preferences and his/her current environment. On the practical side, all those nice computations require energy and computing power (especially if computer vision is involved), and the system needs to be easy to carry around and use.
I am currently reviewing available systems both commercial and prototypes. I will post my progress on this blog.

Welcome

Welcome to MultiNav, my online journal about multimodal navigation aids. At the moment I am doing my mester's thesis project in this area. More info to come!