Ausarbeitung/conclusion.tex

   1 \chapter{Conclusion and Future Work}
   2 The previous chapters have presented the original motion behavior of the
   3 Roomba, besides two different approaches to improve dead reckoning. This goal
   4 could be reached only in parts, for laminated floors using the mean correction
   5 in Experiment~2. However, there is still many potential to work towards that
   6 goal.
   7
   8 The set of measured data in this work was relatively small to serve as a
   9 good representation of the world. Only two types of floors were used, and a
  10 fixed set of parameters for the movements. One possibility here is to widen the
  11 data set, probably using not only fixed values but maybe also a stochastic
  12 approach to determine the input values. Furthermore, only the target distance
  13 resp. orientation, and the velocity were considered as factors to affect the
  14 measured value. There are still much other factors to consider, for example the
  15 voltage and capacity of the Roomba's internal battery. Also, the Roomba can
  16 move not only in straight lines and turn on the spot, but also drive arcs.
  17 Additionally, it is not sure how different robots or different Roomba
  18 models behave when it comes to movement.
  19
  20 As mentioned in Section~\ref{sec:exp2:results}, a quadratic regression could be
  21 applied to the data, which results in a better fit function and a closer
  22 approximation to the measured data. This may probably improve the mean
  23 correction approach from Experiment~2, and also correct errors better when
  24 driving on carpet floors.