1

17.08.2021 Meeting Notes

|

Meeting Details

Date : 17th August 2021

Time : 11:00 – 12:00

Location : Chair of CPS, Montanuniverität Leoben

Participants: Univ.-Prof. Dr. Elmar Rueckert, Vedant Dave

Agenda

First Project Topic Finalization

Topic 1: Demonstration of ProMPs in Franka

  1. 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.
  2. Simulate the retrieved trajectory in ROS on Franka Arm.
  3. Implement the simulated trajectory in real world Franka Arm.

Topic 2: Initial research topic

  1. 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.
    •  
  2. ProMPs with Reinforcement Learning
    • Might be used to find the optimal way of grasping the objects.
    • Integrate it with the transfer learning model. 

Next Steps

  1. Implement ProMPs in python, then in simulation  and then in the real world robot.
  2. Try to provide an instance of the mathematical model to integrate the ProMPs with Transfer Learning.

Literature

ProMPs with Latent Manifolds

  1. 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

  1. Seker, M., Imre, M., Piater, J., & Ugur, E. (2019). Conditional Neural Movement Primitives. Robotics: Science and Systems
  2. 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

  1. 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.
  2. Finn, Chelsea, P. Abbeel and Sergey Levine. “Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks.” ICML (2017).  

ProMPs with constraints

  1. Frank, F., Paraschos, A., Smagt, P.V., & Cseke, B. (2021). Constrained Probabilistic Movement Primitives for Robot Trajectory Adaptation. ArXiv, abs/2101.12561.

Next Meeting

Next meeting was scheduled on Thursday, 26th August, 2021. 10:00 am – 11:00 pm.