Progress report 5

Since last time I posted I have been writing more about using non-positioning type sensors in a navigation system. If this approach can be made to work reasonably well, it could be used as a backup in a complete system. I have also been thinking a bit ahead on how to treat data in a system with an arbitrary number of sensors. I have the idea of a model where a position determination is a weighing of different sensor's data, where the weights might perhaps be learnt at runtime, though for example, in an outdoor environment GPS should be the most important, whereas indoors it could be a WLAN positioning system. The model I am thinking of could take other non-positioning sensors into account, which I think could act as a backup, as (if not using vision) we can get a system that is much lighter on computational resources.

This is probably one of the more confusing posts, but I am just starting to think about the model, and more details will come as I go. I'll add a new reference on non-positioning sensors to the bottom of the BiBTeX database right now. The approach used in that paper is machine learning and a "data cooking" module which they claim reduced the navigation error rate of this approach down to 2%.

I will be away for five days. Happy Easter!

Progress Report 4

Progress is a bit slow at the moment. Trying to plan out the next section. In the meantime, I'm adding a chapter on navigation using lasers, and also refining what I've written so far. From tomorrow and on I will have no other course to worry about, which is a good thing as I'm preparing to take on the final chapters of this thesis.

Also, when fed up with writing I've been looking at programming libraries (vision, audio, speech...) and some random things that pop into my head from time to time. I just wish computer vision algorithms were better, as vision has huge potential in a travelling aid for someone who lacks it. I want a system to read informational signs in the environment and to tell me if that bus over there is the right one. I'm also giving self-containment a priority, that is, the device should try to rely as little as possible on external information (which might not exist in some places). That doesn't mean such information is useless, however.

I've also tested an ER1 robot. I am able to move it and have it recognise (and say aloud) objects and follow them. It really likes looking at CD's.

Mobile Robot Navigation Techniques

A very useful resource on the topic: http://www.doc.ic.ac.uk/~nd/surprise_97/journal/vol4/jmd/

Progress Report 3

I have reached a milestone in my work where chapter 2 (theory and related work) is pretty much complete. This is the first time I am writing in a massively parallel style, and am enjoying it. I used to write continuously, but parallelising has several advantages, an important one being the motivational aspect. It felt less secure at first, but I think I am getting used to it.

Today I will do a clean-up of my BiBTeX reference database and upload the whole thing to the resources page on the right.

RFID and Location Identification

I am at the moment reading about RFID and other sensors that might not at first thought be of any use at all in a navigation device. Everything from temperature sensors to magnetometers can be used though, as demonstrated by one of the systems I've seen. This is what I'd like to think of as location fingerprinting. I have collected some references that I am writing about.

I will update the resource page sometime with the new resources. It needs major cleaning up and proper citing as well. I will get around to that sometime!

ER1 Demonstration

Progress Report 2

First off, let's celebrate passing the 4500 word mark, whatever that means. I don't like word or page counting anyway, possibly as little as I do computer spell checkers.

This week I have continued to write about the building blocks (GPS, AGPS, DGPS, WLAN, ...) and have written about two of the most complex systems I have found (Drishti and SWAN). They are excellent prototypes and contain much of the functionality I seek. Interestingly, I haven't encountered any navigation system trying the paradigm of machine learning. As I see it now, there are two major directions to go forward:
1. Make multimodality really work. There are already excellent commercial GPS systems for the blind; It is time to extend that. Find a way to put all kinds of sensors in an efficient device that lasts an acceptable time on batteries. Find clever ways of using all the information and presenting it. Provide some minimal functionality at all times.
2. Let the machine think. One must be careful here, but if done right this could lead to a much easier to use system. One of the important properties I think a system should possess is minimal (and quick) interaction. This is true for mobile devices in general, where it is important to be able to perform tasks quickly.
A system capable of learning would also make adaptation much easier. Users' habis would be picked up and the presentation and behaviour would be adjusted accordingly. Locations that are especially difficult would be noticed and presentation verbosity would be adjusted... Consistency of behaviour is important though, and so if the machine decides to behave differently it has to do so in a way the user expects, or else it could lead to much confusion.

Next week I will write about a couple of other systems, and also polish up this section and check that I actually evalate the systems based on my own recently-established criteria! Also, the pervasive computing viewpoint is something I didn't initially consider, but is something I should definitely consider, as it is a viable future research direction. This paradigm is already applied in some other aids for the disabled including devices for those with dementia.

Also realised something simple and obvious while out walking yesterday with my phone's GPS system: It is by far not enough to just give directions when approaching an intersection, curvy roads can be difficult at times in the winter! In the winter, the world is a new one every day, I use to say.