About Rafael Papallas

Research Overview Image

I am a Research Fellow in the School of Computing at the University of Leeds. My research interest is in robotic manipulation, manipulation planning, motion planning and motion control. I received my PhD from the School of Computing, University of Leeds.

I envision a future where robots co-exist with humans in dynamic environments to empower and improve the quality of their lives. For example, consider a robot at home assisting a motor-impaired person with daily tasks like the one in the figure above. The robot needs to retrieve the orange juice bottle from the back of a cluttered fridge. Other obstacles, at the front of the fridge, prevent the robot from directly reaching and grasping the orange juice bottle successfully. The robot needs to find a plan to manipulate those objects, perhaps by safely pushing them away, to create the required space to reach and grasp the orange juice bottle.

My research deals with such challenging problems where a robot needs to interact with movable objects in cluttered and dynamic environments while reasoning about their dynamics. In particular, I am interested in developing motion planning and control algorithms for non-prehensile physics-based manipulation in clutter. This is a particularly challenging problem today in Robotics. We don’t have robots that can achieve such manipulation effectively in highly cluttered environments like a fridge or a warehouse shelf.

Recent Publications

Please click on each publication to read a brief description, access a pre-print, the paper and the source code.

To ask for help or not to ask: A predictive approach to human-in-the-loop motion planning for robot manipulation tasks

Rafael Papallas and Mehmet Dogar

2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Online Replanning With Human-in-the-Loop for Non-Prehensile Manipulation in Clutter — A Trajectory Optimization Based Approach

Rafael Papallas, Anthony G. Cohn, and Mehmet Dogar

2020 IEEE Robotics and Automation Letters (RA-L)

Non-Prehensile Manipulation in Clutter with Human-In-The-Loop

Rafael Papallas and Mehmet Dogar

2020 IEEE International Conference on Robotics and Automation (ICRA)

Planning with a Receding Horizon for Manipulation in Clutter Using a Learned Value Function

Wissam Bejjani, Rafael Papallas, Matteo Leonetti and Mehmet Dogar

2018 IEEE-RAS International Conference on Humanoid Robots

Experience

Research Fellow in Robotic Manipulation

University of Leeds (2021-Today)
University of Leeds Logo
I am currently working on an exciting UKRI/EPSRC project in robotic manipulation and my main research focus is in motion planning and motion control.

Software Developer

Cimlogic (2015-2016)
Cimlogic Logo

I spent a year working in industry as part of my degree.

  • I worked with a range of Microsoft technologies, including C#, SQL Server, and ASP.NET.
  • Contributed to big projects and deployed software for big manufacturing firms.
  • Contributed to development of internal tools.

Education

Doctor of Philosophy, PhD

School of Computing, University of Leeds (2017-2021)
School of Computing, University of Leeds Logo
  • Research focus: robotics; robotic manipulation; physics-based motion planning; motion control.
  • Recipient of a UKRI-EPSRC Doctoral Training Partnership (DTP) scholarship.

B.Sc. Computer Science (Industrial)

School of Computing, University of Leeds (2013-2017)
School of Computing, University of Leeds Logo
  • Core Computer Science degree with a year spent working as a Software Developer in industry
  • My individual final year project investigated and implemented a robot cashier.