1 code implementation • 10 Jul 2017 • Rouhollah Rahmatizadeh, Pooya Abolghasemi, Ladislau Bölöni, Sergey Levine
We propose a technique for multi-task learning from demonstration that trains the controller of a low-cost robotic arm to accomplish several complex picking and placing tasks, as well as non-prehensile manipulation.
no code implementations • 17 Oct 2016 • Jun Xu, Gurkan Solmaz, Rouhollah Rahmatizadeh, Damla Turgut, Ladislau Boloni
To achieve the information efficiently, we propose a path planning approach for the UAV based on a Markov decision process (MDP) model.
no code implementations • 12 Mar 2016 • Rouhollah Rahmatizadeh, Pooya Abolghasemi, Aman Behal, Ladislau Bölöni
Our experimental studies validate the three contributions of the paper: (1) the controller learned from virtual demonstrations can be used to successfully perform the manipulation tasks on a physical robot, (2) the LSTM+MDN architectural choice outperforms other choices, such as the use of feedforward networks and mean-squared error based training signals and (3) allowing imperfect demonstrations in the training set also allows the controller to learn how to correct its manipulation mistakes.