Master Thesis on “Reinforcement Learning for deformable object manipulation”

Supervisor: Prof. Ville Kyrki (ville.kyrki@aalto.fi)
Advisors: MSc. David Blanco Mulero (david.blancomulero@aalto.fi), MSc. Karol Arndt (karol.arndt@aalto.fi), PhD. Gökhan Alcan (gokhan.alcan@aalto.fi).

Keywords: reinforcement learning, robot learning and manipulation.

Project description

Reinforcement Learning (RL) has shown great results on tasks like learning to play games or dexterous manipulation. However, tasks like manipulation of deformable objects like cloth are still far from being solved. Recent approaches have focused on applying dynamic manipulation together with Reinforcement Learning for cloth manipulation tasks, such as unfolding or folding fabrics.

This thesis will focus on how to applying RL methods for solving cloth manipulation tasks. The thesis will explore the state-of-the-art and work on solutions for cloth manipulation.

Previous knowledge on Machine Learning is desired.

Deliverables

  • Review relevant RL literature,
  • Implementation of relevant RL algorithms,
  • Evaluation of the experimental results,
  • Evaluation of algorithms on real robots.

Practical information

Pre-requisites: Python (high/medium), Reinforcement Learning (medium), Machine Learning (medium)

Tools: OpenAI gym, Softgym/MuJoCo/PyBullet

Start: Available Immediately

References

Lin, Xingyu, Yufei Wang, and David Held. “Learning Visible Connectivity Dynamics for Cloth Smoothing.” arXiv preprint arXiv:2105.10389 (2021).

Hietala, Julius, et al. “Closing the Sim2Real Gap in Dynamic Cloth Manipulation.” arXiv preprint arXiv:2109.04771 (2021).

Ha, Huy, and Shuran Song. “Flingbot: The unreasonable effectiveness of dynamic manipulation for cloth unfolding.” Conference on Robot Learning. PMLR, 2022.