PhD Thesis direction initiation
Topic 1: Improvement in Riemannian Approach
- Closed form solution for the Cost function instead of Gradient Descent.
- Decreasing computational time algorithmically or with parallel computing.
- ProMPs on Mixture Manifolds: ℝ3 × 𝕊3.
Topic 2: Topics of Possible Research Directions
- Conditional Neural Movement Primitives
- Implement the initial approach.
- Develop this approach for Orientation and full ProMPs.
- The part of Control is missing from the paper, which can be worked upon.
- ProMPs with Reinforcement Learning
- Use Reinforcement Learning to learn the model outside the demonstrated trajectory distribution.
- Reinforcement Learning for generalizing to new configurations.
- ProMPs wit Transfer Learning
- Search the research papers focusing on both, Movement Primitives and Transfer learning. The advantage lies in learning from minimal training data.
- Look up papers for combining the Model-agnostic Meta learning with Movement Primitives.
- Planning as Inference
- Read up for Research paper concerning the topic.
- Online trajectory modulation.
- Human-Machine Interaction and Control
- ProMPs with latent manifolds
- Constrained Probabilistic Movement Primitives
- Understand the approach of the recent paper and check for any other possible improvement and possible research direction.
- Search for relevant research papers in those fields.
- Finalise the first project to work on.
- Meet and discuss the topic with Nicolas. Also make the topic adaptable to his Master Thesis.
ProMPs with Latent Manifolds
- Rückert EA, Neumann G. Stochastic optimal control methods for investigating the power of morphological computation. Artif Life. 2013 Winter;19(1):115-31. doi: 10.1162/ARTL_a_00085. Epub 2012 Nov 27. PMID: 23186345.
Conditional Neural Movement Primitives
- Seker, M., Imre, M., Piater, J., & Ugur, E. (2019). Conditional Neural Movement Primitives. Robotics: Science and Systems
- Garnelo, Marta & Rosenbaum, Dan & Maddison, Christopher & Ramalho, Tiago & Saxton, David & Shanahan, Murray & Teh, Yee & Rezende, Danilo & Eslami, S.. (2018). Conditional Neural Processes.
ProMPs wit Transfer Learning
- Stark, S., Jan Peters and Elmar Rueckert. “Experience Reuse with Probabilistic Movement Primitives.” 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (2019): 1210-1217.
- Finn, Chelsea, P. Abbeel and Sergey Levine. “Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks.” ICML (2017).
ProMPs with constraints
- Frank, F., Paraschos, A., Smagt, P.V., & Cseke, B. (2021). Constrained Probabilistic Movement Primitives for Robot Trajectory Adaptation. ArXiv, abs/2101.12561.
Next meeting was scheduled on Tuesday, 17th August, 2021. 11:00 am – 12:00 pm.