Machine learning and automation are two interconnected fields that have revolutionized various industries and processes. Machine learning is the use of algorithms and statistical models that allow computer systems to improve their performance on a specific task through experience and data, without the need for explicit programming. Automation, on the other hand, involves the use of technology to perform tasks with minimal human intervention. This article examines current machine learning techniques to automatically define planning knowledge. It was organized according to the objective of the learning process: automatic definition of planning action models and automatic definition of planning control knowledge.