Particle filter

[stevenwaslander]

Needs to be functionalized, and made more efficient. Multiple examples are needed. Must work for flyover example, and feature localization.

[chutsu]

Signing myself up for this one.

[chutsu]

I have a question, so in the old code there are quite a few examples, some of which I'm not sure whether I should refactor them?:

• ellipse.m
• importance.m
• nonlinear.m
• nonlinearmapping.m
• normal.m
• reesampling.m

Or should I just refactor exactly two examples, flyover example and the feature localization example.

[stevenwaslander]

Woah, not sure what all those are, do they all work? You're welcome
to only focus on the EKF/UKFSlam example, the others may be junk
files or different examples.

Steve

On 2/29/2016 2:40 PM, Christopher Choi
  wrote:

  I have a question, so in the old code there are quite a few
    examples, some of which I'm not sure whether I should refactor
    them?:

    ellipse.m
    importance.m
    nonlinear.m
    nonlinearmapping.m
    normal.m
    reesampling.m

  Or should I just refactor exactly two examples, flyover example
    and the feature localization example.
  —
    Reply to this email directly or view
      it on GitHub.

[chutsu]

Haha, too late I already refactored them. The files are not as pointless as we first thought, they are actually the code that produces some of the plots in Estimation I and II slides. e.g. resampling.m corresponds to the particle deprivation problem, nonlinear.m plots the linear and nonlinear transform, how a nonlinear transform does not preserve a gaussian distribution, relevant slides 99 to 101 (kind of..) in Estimation I.

[chutsu]

Also do you mind if I just do the Particle Localization of the old ME597-6-ParticleLocalization code? I feel if I do the EKF/UKFSlam it goes beyond this issue's scope.

[stevenwaslander]

Sounds good.

[chutsu]

Done, please see PR #32