Assoc. Prof. Emre Uğur from Boğaziçi University will be the next guest on ROMER Talks on Friday November 18th @12:30. The face-to-face seminar will be held at BMB-5, at the Department of Computer Engineering. You can also join us via Zoom using the following link.

Zoom Link: https://zoom.us/j/93443337016?pwd=WlhreU0zTy9mZVkzRVIxRlhwWFZzQT09

Please feel free to share and join us at the seminar.

Title: Learning Complex Robotic Skills via Conditional Neural Movement

Primitives

Abstract: Predicting the consequences of one's own actions is an

important requirement for safe human-robot collaboration and its

application to personal robotics. Neurophysiological and behavioral

data suggest that the human brain benefits from internal forward

models that continuously predict the outcomes of the generated motor

commands for trajectory planning, movement control, and multi-step

planning. In this talk, I will present our recent Learning from

Demonstration framework [1] that is based on Conditioned Neural

Processes. CNMPs extract the prior knowledge directly from the

training data by sampling observations from it, and use it to predict

a conditional distribution over any other target points. CNMPs

specifically learn complex temporal multi-modal sensorimotor relations

in connection with external parameters and goals; produce movement

trajectories in joint or task space; and execute these trajectories

through a high-level feedback control loop. Conditioned with an

external goal that is encoded in the sensorimotor space of the robot,

predicted sensorimotor trajectory that is expected to be observed

during the successful execution of the task is generated by the CNMP,

and the corresponding motor commands are executed. After presenting

the basic CNMP framework, I will talk about how to form flexible

skills combining Learning from Demonstration and Reinforcement

Learning via Representation Sharing [2], and the deep modality

blending networks (DMBN) [3], which creates a common latent space from

multi-modal experience of a robot by blending multi-modal signals with

a stochastic weighting mechanism.

References:

[1] Seker et al. Conditional Neural Movement Primitives, Robotics:

Science and Systems (RSS), 2019

[2] Akbulut et al. ACNMP: Flexible Skill Formation with Learning from

Demonstration and Reinforcement Learning via Representation Sharing,

Conference on Robot Learning (CoRL), 2020

[3] Seker et al. Imitation and Mirror Systems in Robots through Deep

Modality Blending Networks, Neural Networks, 146, pp. 22-35, 2022

Bio: Emre Ugur is an Associate Professor in Dept. of Computer

Engineering, Bogazici University, the chair of the Cognitive Science

MA Program, the vice-chair of the Dept. of Computer Engineering, and

the head of the Cognition, Learning and Robotics (CoLoRs) lab

(https://colors.cmpe.boun.edu.tr/). He received his BS, MSc, and Ph.D.

degrees in Computer Engineering from Middle East Technical University

(METU, Turkey). He was a research assistant in KOVAN Lab. METU

(2003-2009); worked as a research scientist at ATR, Japan (2009-2013);

visited Osaka University as a specially appointed Assist.&Assoc.

Professor (2015&2016); and worked as a senior researcher at the

University of Innsbruck (2013-2016). He was the Principle Investigator

of the IMAGINE project supported by the European Commission. He is

currently PI of the EXO-AI-FLEX and Deepsym projects supported by

TUBITAK. He is interested in robotics, robot learning, and cognitive

robotics.


Last Updated:
12/11/2022 - 22:34