Movement

I was interested in using a particle filter to provide the robots more stable movement. The particle filter uses three ultrasonic sensors to provide the NXT with an idea about its location in the surrounding environment. The particle filter is based on a style of probabilistic localization called Monte-Carlo Localization. It relies on finding the best odds from a series of seemingly random outcomes. Particle filters are horribly computationally intensive with lots of floating point math.

In Monte-Carlo Localization a large number of hypothetical current configurations are initially randomly scattered in configuration space. With each sensor update, the probability that each hypothetical configuration is correct is updated based on a statistical model of the sensors and Bayes' theorem. Similarly, every motion the robot undergoes is applied in a statistical sense to the hypothetical configurations based on a statistical motion model. When the probability of a hypothetical configuration becomes very low, it is replaced with a new random configuration.

Due to the time limit, I didn’t have a chance to work much on coding it and using with my algorithm, so I will not be working on this anymore, but I will still do personal research about this subject at a later time.

Time: 6hrs