Motion planning is a relevant research area in robotics and its purpose is to find a collision-free path from a start to a goal robot configuration. Especially for manipulator arms, planning problems require contact-rich interactions between a robot and the objects in the environment without collision. There are several techniques to solve these problems, such as search-based and sampling-based algorithms. Besides these techniques, learning-based methods are used to enhance efficiency at solving motion planning problems. Generally, the learning-based techniques applied to robot motion planning can be classified as supervised, unsupervised and reinforcement learning. With the increasing popularity of learning techniques, new frameworks/libraries have been proposed to automatically find the optimal path. This project aims to implement and test state-of-the-art learning-based motion planning approaches that determine the optimal path for a manipulator toward the goal configuration. More specifically, the test will define a start-to-goal problem in a space with obstacles. The start-to-goal problem will be solved by using the implemented learning-based motion planning approaches, and according to the results obtained, the implemented approaches will be evaluated to prove their feasibility. The expected output of the project is to have an implementation of one or more machine learning based motion planning approaches and an evaluation of them. The student will need to research existing works in learning-based motion planning approaches. Such motion planning approaches, and the test environment will be fully developed and implemented over the robot operating system (ROS). Prerequisites: - Experience in software development (Python or C/C++). - Experience with Linux is desirable. If not familiar with Linux, it would be necessary to learn while doing the project. - Experience with ROS is desirable. If not familiar with ROS, it would be necessary to learn while doing the project. - Interest in learning about robotics in general.