Рет қаралды 587
Presenter: Georgia Chalvatzaki
(www.ias.inform...)
Title: Towards intelligent robotic assistants: human perception,
accelerated skill learning, and adaptive planning
Abstract:
Societal facts like the increase in life expectancy, the lack of
nursing staff, the hectic rhythms of everyday life, and the recent
unprecedented situation of the Covid-19 pandemic make the need for
intelligent robotic assistants more urgent than ever. Spanning their
applications from home-environments to hospitals, workhouses to
agricultural development, etc., the embodied AI robotic assistants are
in the epicenter of modern robotics and AI research. In this talk, I
will go through my research work for developing intelligent methods
for such assistive agents. We will draw the big picture of intelligent
service robots, and we will specifically focus on sub-problems that I
have tackled in the last few years. The main research areas we will
cover: the perception and recognition of human activities, combining
classical methods like tracking with machine learning for robot action
planning and control; algorithms for encoding object-features that
allow 6D tracking and grasp-planning; we will discuss methods that can
leverage human-centered information for learning intelligent robot
behavior using reinforcement learning; I will elaborate on our recent
work about accelerated policy learning of manipulation tasks, and
lastly, I will refer to our recent work for task and motion planning
over an extended decision space of diverse task plan-skeletons and
continuous parameters over actions. While these topics cover only
partial aspects of the bigger problem, we will discuss the open
research questions on the combination of learning, reasoning, and
planning in unstructured environments using mobile manipulator robots.
Mobile manipulators are the most emblematic systems to encapsulate the
benefits of embodied AI research towards achieving the long-term
vision of developing intelligent robotic assistants.
Short bio:
Georgia Chalvatzaki is the research leader of the new intelligent
robotic systems and assistants (iROSA) group at TU Darmstadt. She has
recently been accepted into the renowned Emmy Noether Programme (ENP)
of the German Research Foundation (DFG) - only 9 proposals out of 91
proposals were selected for funding. ENP enables outstanding young
scientists to qualify for a university professorship by independently
leading a junior research group over six years. In her research group
iROSA, her team will research the topic of "Robot Learning of Mobile
Manipulation for Assistive Robotics", investigating novel methods for
combined planning and learning for enabling mobile manipulator robots
to solve complex tasks in house-like environments, with the
human-in-the-loop of the interaction process.
Before that, she was a Postdoctoral researcher from October 2019 till
January 2020 at the Intelligent Autonomous Systems (IAS) group of
Prof. Jan Peters in the Department of Computer Science at TU
Darmstadt. She completed her Ph.D. studies in 2019 at the Intelligent
Robotics and Automation Lab, advised by Prof. Costas Tzafestas and
Prof. Petros Maragos, of the National Technical University of Athens,
in Greece. Her thesis topic is "Human-Centered Modeling for Assistive
Robotics: Stochastic Estimation and Robot Learning in Decision
Making." During her research career, she has worked on eight research
projects, and she has published more than 30 papers, most of which in
top-tier robotics and machine learning venues, e.g., ICRA, IROS, RA-L.
Georgia is currently nominated for the title of AI-Newcomer 2021 by
the German Informatics Society.
Organized by the Intelligent Systems Lab at TU Berlin (argmin.lis.tu-....
Moderated by Andreas Orthey (aorthey.de/) and Marc Toussaint (www.marc-toussa....