The field of robotics and automation has seen tremendous advancements in recent years, with a focus on enhancing the capabilities of robots to interact with the real world. One of the most challenging tasks for robots is the manipulation of novel objects in cluttered environments. This research involves the convergence of several cutting-edge technologies, including machine learning, computer vision, and computational robotics.

This project aims to develop a framework to recognise and move novel objects from one pose to another pose. More specifically, the test will include multiple objects to manipulate in a cluttered space. The detection of objects’ poses will be solved by using grasping planning algorithms and the manipulation of objects will be solved by using motion planning algorithms. The expected output of the project is to develop a framework that integrated a grasping planner and motion planner, as well as, their evaluation and benchmarking.

The student will need to research existing works grasping and motion planning approaches. Such 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.