Learning to Cooperate in Multi-robot Task Allocation
ApplyProject Description
Imagine robots self-organizing into large groups to assist people with physically demanding tasks, leveraging their core capabilities in perception, manipulation, and navigation to interact with the physical world. To successfully complete a given mission as a team, these robots must make their own decisions to allocate and carry out tasks defined in the mission and cooperate with one another when the task requires it. We realize this capability in multirobot systems through a learning-based paradigm, designing computational models to train a large number of robots to work as a team. Achieving a high level of autonomy in distributed information processing, decision-making, and collaborative manipulation is crucial. To enable a high level of cooperation among a large number of robots, the project aims to build computational models based on deep reinforcement learning (DRL). These models are designed to enhance the robots' ability to cooperate in carrying out multiple tasks using their perception, manipulation, and navigation skills. Additionally, the project's goal is to implement these models on a multi-robot platform and validate the effectiveness of the models through lab experiments.
Program -
Electrical Engineering
Division -
Computer, Electrical and Mathematical Sciences and Engineering
Faculty Lab Link -
https://cemse.kaust.edu.sa/dsa
Field of Study -
Electrical and Computer Enginnering
About the
Researcher
Shinkyu Park
Desired Project Deliverables
The main objective of this project is to implement multi-agent DRL in a team of mobile manipulators and validate our DRL implementation through lab experiments. Students are expected to collaborate with lab members to explore new ideas and implement them on physical robotic systems. To fulfill the requirements of the project, students should have solid experience working with robotic systems and the Robot Operating System, as well as confidence in C++/Python programming. Experience with reinforcement learning is a plus. The model design and experiment reports are expected to be delivered at the end of the internship program.