First Project Topic Finalization
Topic 1: Demonstration of ProMPs in Franka
- Implement Probabilistic Movement Primitives in Python. Initially it only includes retrieving the mean and the via-point trajectory. We can then extend the implementataion to some parameters etc.
- Simulate the retrieved trajectory in ROS on Franka Arm.
- Implement the simulated trajectory in real world Franka Arm.
Topic 2: Initial research topic
- Probabilistic Movement Primitives with Transfer Learning
- Integrate Transfer learning with Movement Primitives.
- Approach the generalization on the primititvies on the basis of morphology.
- Use robot hand with tactile sensor for acquiring the data.
- ProMPs with Reinforcement Learning
- Might be used to find the optimal way of grasping the objects.
- Integrate it with the transfer learning model.
- Implement ProMPs in python, then in simulation and then in the real world robot.
- Try to provide an instance of the mathematical model to integrate the ProMPs with Transfer Learning.
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 Thursday, 26th August, 2021. 10:00 am – 11:00 pm.