Dr.Hebah ElGibreen is an associate professor at the Department of Information Technology, College of Computer and Information Sciences, King Saud University. She is currently the director of AI Center of Advanced studies at KSU while leading the female branch of the Center of Smart Robotics Research at her college. Dr.Hebah received her PhD degrees from King Saud University in 2015, where she specialized in artificial intelligence and machine learning. She got her post-doc from Massachusetts Institute of Technology (MIT) in 2017 and continued as research affiliate with the Mechanical Engineering department (MRL Lab) until 2021. Currently, her research focuses on using ML approaches to improve collaborative robotics motions in a shared environment. In the past couple of years, she was able to publish part of her work in different ISI journals. She is still ongoing with her project and looking for ways to integrate cognitive learning in order to apply innovative solutions that can be applied to more complex areas, including health and industry 4.0.
MIT Fellowship Research Abstract:
Robots are becoming more common and widespread around the world. Collaborative robotic is one area that has been recently under the spot light, especially in the industrial community. This type of robot work in shared environment with humans to perform different tasks safely and efficiently. This causes the robots to be more of companion and human partners than simple machines that do a certain task. This companionship introduces the benefit of human strength in addition to the full benefit of robots. However, performing time/safety critical tasks lead to more challenges.
In collaborative robotics, machines behavior must be clear and understood. The robots should have the ability to interact with each other and efficiently finish their task in shared environment. This can be accomplished by improving the capability of allocating dynamic and partially observed tasks to efficiently finish the job. However, this is a challenge due to the environment variability and uncertainty which introduce large and continuous space that is difficult for the machine to process. Machine Learning (ML) is one area of artificial intelligence that can be applied to develop autonomous policies. Learning and planning ability introduced by ML can also be extended to enable robot to predict others movements and plan its next task.
This research will focus on using ML techniques to improve collaborative robotics interaction in shared environment. The main objective is to improve the efficiency of robots’ interaction in a shared and dynamic environment through continuous planning and prediction. Machine language is one of the approaches that will be considered to answer some of the challenges observed in collaborative robotics, such as uncertain constraint and dynamic multi-agent allocation.