The previous subsections were about understanding AIML tags and how to work with them using the PyAIML module. Let's see how to create an interactive AIML bot using ROS. The following figure shows the complete block diagram of the interactive bot:

Figure 4: Interactive AIML bot

Here is how the entire system works: The speech of the user is converted into text using the speech recognition system in ROS. Then, it will input either to the AIML engine or send as a robot command. The robot commands are specific commands meant for robot control. If the text is not a robot command, it will send it to the AIML engine, which will give an intelligent reply from its database. The output of the AIML interpreter will be converted to speech using the text-to-speech module. The speech will be heard through speaker at the same time a virtual face of the robot will be animated on the screen, syncing with the speech.

In this chapter, we are mainly dealing with the AIML part and TTS using ROS; you can refer to other sources to perform speech recognition in ROS as well.