I have a robot that I need to write an autonomous program for. The program is to play on this feild: http://www.vexforum.com/wiki/index.php/Gateway.
and pick up the balls and barrels and put them in the cylinders(goals). I have sensors like light detection(best for following white line on ground or keeping track of location by noticing when you cross a white line), ultrasonic sonar, bump sensors, and encoders(count amount of wheel rotations). I want to make a program where the program learns the field and learns how to navigate best with the tasks at hand. I am thinking a neural net is my best choice but I can't think of what inputs I would use. The main thing is I don't want scripted paths. I know this is pretty vague but too much detail and no one would read this. Anyone ave any ideas?
Check out Udacity course 373by Prof Thurn at http://www.udacity.com/overview/Course/cs373.
He has successfully applied 'particle filters' to program the Google Driveless car
You need to use Simultaneous localization and mapping (SLAM)
It is a pretty standard and successful technique for robot localization.
Related
I am working on a smartwatch project. I want the display to be turned off and only come on when the user brings his hand into the watch-viewing position.
I am running my application on the NRF52 MCU which means machine learning is out of the question. I am using a 3-axis accelerometer from STM.
How can I detect when a user moves his hand into the typically watch viewing position? How is this achieved in smartwatches?
I have the following ideas so far:
- Constantly poll accelerometer and calculate pitch and roll values. Then determine what range of pitch and roll values corresponds to this gesture. This seems a bit wasteful because the CPU will have to be always active.
Is there a simple signal processing algorithm or something similar that can achieve this?
Look into Galvanic skin response sensor - It can measure electrical connectivity of the skin.
When internal or external forces cause arousal — of any kind — the skin becomes a better conductor of electricity. Essentially, when you start to sweat, either from exercise or something else, the band will be able to monitor that.
Detecting when someone is sweating gives the software more information about what a user is doing, which allows for better health tracking. Being able to correlate the level of activity with a different source than just gravity from the accelerometer, allows these programs to take on a more trainer-like role — recommending specific exercises and levels of exertion.
Hope this helps!
Im currently designing a robot for my undergraduate project. One of the task of this robot is to follow the wall. For the purpose I'm using a PID control system, where the reference is given from a ultrasonic sensor. So my problem here is im having a hard time tuning the PID. I know i can find the P coefficient pretty easily by plotting the desired set point range vs desired motor output speed. Even then the robot is not so stable, so i though of adding DI part of PID. But how do find out roughly the values of these coefficients without just trying out random values (manual tuning)?
Thank you so much. Much appreciated. Sorry for a unrelated post on stackExchange. I believe programmers have a deep insight thinking than an engineer ;) Have a nice day
I am getting the gps position and time of a voluntary person which moves around. I am acquiring the position every second with Matlab and save it in a matrix.
Now I would like to be able to say if the person is moving normal or not. For example running in circles is not normal for a person who usually only walks around.
I am not looking for a complete solution because I would like to learn through my project and understand every aspect. I would be very grateful if you could show me the right direction. Good literature, tutorials and simple catchwords would also be very helpful for me because at the moment I dont know how to approach my problem.
Thank you very much in advance!
Kind regards,
Tom
What you're looking for is anomaly detection. The primary commercial application of this technology is in fraud detection. As for pointing to resources any books that cover data mining should have a section about anomaly detection.
Something to for warn you about, it sounds from your description that you will be working with time series data which is its own branch of data mining.
Catchwords: Anomaly Detection, and Time Series Data.
Books: ISBN-13 978-0321321367 Introduction to Data Mining (This is a good starting point if you don't have a lot of background in the subject)
I am a beginner in image processing. I want to write an application in C++ or in C# for
Searching an image in a list of images
Searching for a particular feature (for e.g. face) in a list of images.
Can anybody suggest where should I start from?
What all should I learn before doing this?
Where can I find the correct information regarding this?
In terms of the second one, you should start off with learning how to solve the decision problem of whether a square patch contains a face (or whatever kind of object you are interested in). For that, I suggest you study a little bit of machine learning, the AdaBoost algorithm, Haar features, and Viola-Jones.
Once you know how to do that, the trick is really just to take a sliding window across your image, feeding the contents of that window into your detector. Then you shrink your main input image and repeat the process until your input image has gotten smaller than the minimum size input for your detector. There are, of course, several clever ways to parallelize the computation and speed it up, but the binary detector is really the interesting part of the process.
You may find some of the material linked from the CSE 517: Machine Learning - Syllabus helpful in getting into machine learning and understanding AdaBoost. You will certainly find the Viola-Jones paper of interest.
Disclaimer: I'm not actually trying to make one I'm just curious as to how it could be done.
When I say "Most Accurate" I include the basics
wall
distance
light levels
and the more complicated
Dust in Atmosphere
rain, sleet, snow
clouds
vegetation
smoke
fire
If I were to want to program this, what resources should I look into and what things should I watch out for?
Also, are there any relevant books on the theory behind line of sight including all these variables?
I personally don't know too much about this topic but a quick couple of Google searches turns up some formal papers that contain some very relevant information:
http://www.tecgraf.puc-rio.br/publications/artigo_1999_efficient_lineofsight_algorithms.pdf - Provides a detailed description of two different methods of efficiently performing an LOS calculation, along with issues involved
http://www.agc.army.mil/operations/programs/LOS/LOS%20Compendium.doc - This one aims to maintain "a current list of unique LOS algorithms"; it has a section listing quite a few and describing them in detail with a focus on military applications.
Hope this helps!
Typically, one represents the world as a set of volumes of space held in some kind of space partitioning data structure, then intersects the ray representing your "line of sight" with that structure to find the set of objects it hits; these are then walked in order from ray origin to determine the overall result. Reflective objects cause further rays to be fired, opaque objects stop the walk and semitransparent objects partially contribute to the result.
You might like to read up on ray tracing; there is a great body of literature on the subject and well-understood ways of solving what are basically the same problems you list exist.
The obvious question is do you really want the most accurate, and why?
I've worked on games that depended on line of sight and you really need to think clearly about what kind of line of sight you want.
First, can the AI see any part of your body? Or are you talking about "eye to eye" LOS?
Second, if the player's camera view is not his avatar's eye view, the player will not perceive your highly accurate LOS as highly accurate. At which point inaccuracies are fine.
I'm not trying to dissuade you, but remember that player experience is #1, and that might mean not having the best LOS.
A good friend of mine has done the AI for a long=-running series of popular console games. He often tells a story about how the AIs are most interesting (and fun) in the first game, because they stumble into you rather than see you from afar. Now, he has great LOS and spends his time trying to dumb them down to make them as fun as they were in the first game.
So why are you doing this? Does the game need it? Or do you just want the challenge?
There is no "one algorithm" for these since the inputs are not well defined.
If you treat Dust-In-Atmosphere as a constant value then there is an algorithm that can take it into account, but the fact is that dust levels will vary from point to point, and thus the algorithm you want needs to be aware of how your dust-data is structured.
The most used algorithm in todays ray-tracers is just incremental ray-marching, which is by definition not correct, but it does approximate the Ultimate Answer to a fair degree.
Even if you managed to incorporate all these properties into a single master-algorithm, you'd still have to somehow deal with how different people perceive the same setting. Some people are near-sighted, some far-sighted. Then there's the colour-blind. Not to mention that Dust-In-Atmosphere levels also affect tear-glands, which in turn affects visibility. And then there's the whole dichotomy between what people are actually seeying and what they think they are seeying...
There are far too many variables here to aim for a unified solution. Treat your environment as a voxelated space and shoot your rays through it. I suspect that's the only solution you'll be able to complete within a single lifetime...