12.1 Real world example: Robocar

One of the machine learning applications which has high public attention is self-driving cars. All big car manufactures, suppliers and tech companies are working feverish on this topic. But there are also great concerns about safety and ethics which need to be addressed.

Safety of a machine learning algorithm can be increased if the understanding of how the algorithm reaches its decisions. For computer vision this can be done with techniques like keras-salient-object-visualization described in chapter 12.6.

Utilizing this technique on the RC-Robocar framework Donkeycar yields to a movie like the following movie in which the pixels which the algorithm pays attention to are colorized. The green line gives the steering command at the time of recording, the colored pixels indicates the regions in input images by which the algorithm makes its steering decisions, i. e., the salient objects.

Salient-object-visualization:

• Indicates the regions in input images by which the algorithm makes its steering decisions
• Helps to find sources of distractions
  - reflections
  - windows
• Helps to identify solutions
  - crop top of image