SCITOS G5 Mobile Robot Navigation Task.
The data were collected as the SCITOS G5 navigates through the room following the wall in a clockwise direction, To navigate, the robot uses 24 ultrasound sensors arranged circularly around its "waist". The numbering of the ultrasound sensors contains the raw values of the measurements of all 24 ultrasound sensors and the corresponding class label . Sensor readings are sampled at a rate of 9 samples per second. These 24 sensors were set 15° separated from one another
Wall-following robots are used in many applications, including: Automation in industries, Military applications, Consumer applications, Cleaning processes, Domestic purposes
Different number of sensor readings were built in order to evaluate the performance of the classifiers with respect to the number of inputs. Multiclass Classification applied
Tools: Python, Tableau Platform : Jupyter Notebook, aws cloud Library Used : Scikit-Learn, Pandas, Matplotlib, Numpy
Class Distribution: -- Move-Forward: 2205 samples (40.41%). -- Slight-Left-Turn : 826 samples (15.13%). -- Sharp -Right-Turn : 328 samples (6.01%). -- Slight-Right-Turn: 2097 samples (38.43%).