Archive

This summer school will bring together internationally renowned senior experts and young researchers from computer and cognitive sciences, robotics, biomechanics, interaction design, and philosophy to present, discuss and explore recent advances to cognitive architectures. Focusing on the perspectives of modularity, adaptivity, interaction, shared autonomy and inter-subjectivity the five-day programme is organized around keynote talks by senior experts and hands-on workshops on instances of hypothesis-driven system building.

Participants will learn to build state-of-the-art cognitive architectures using robotic platforms available at the CITEC labs such as the small and modular robot platform AMiRo (Autonomous Mini Robot), iCub, SoftBank’s Pepper robot, or a bi-manual manipulator setup with anthropomorphic hands. Beyond the courses and the talks of the invited speakers, the attendance will provide ample opportunities for discussions, and the exchange of ideas. Participants are encouraged to raise questions and bring in their own ideas, which may focus on testing hypotheses, modelling cognitive architectures, implementing specific behavioural functions, expanding past models, or provide a proof-of-concept. Please feel free to describe your ideas in your letter of motivation. The focus can be on software or hardware related topics, or a combination of both.

 

For more information in the program, visit the Summer School's website.

The next strategic meeting of the TN-IIS will be held at Queensland University of Technology. Scientists are invited to get to know QUT, discuss research, develop joint projects and to strengthen and increase our collaboration. Please contact Daniela Urbansky for more information and participation. A program will be developed fitting to the participants research interests.

 

"What’s out there? Novel Imaging Systems for Ocean Exploration"

Abstract:

The ocean covers 70% of the earth surface, and influences almost every aspect in our life, such as climate, fuel, security, and food. The ocean is a complex, vast foreign environment that is hard to explore and therefore much about it is still unknown. Interestingly, only 5% of the ocean floor has been seen so far and there are still many open marine science questions. All over the world, including Israel, depleting resources on land are encouraging increased human activity in the ocean, for example: gas drilling, desalination plants, port constructions, aquaculture, fish farming, producing bio-fuel, and more. As human access to most of the ocean is very limited, novel imaging systems and computer vision methods have the potential to reveal new information about the ocean that is currently unknown. Thus, the future calls for substantial related research in computer vision. The uncertainty stems from the fact that the ocean poses numerous challenges such as handling optics through a medium, movement, limited resources, communications, power management, and autonomous decisions, while operating in a large-scale environment. 
In the talk I will give an overview of the challenges in this field and will present novel algorithms and systems we have developed.

 

Tali is professor at the University of Haifa, Israel and head of the Marine Imaging Lab, Charney School of Marine Sciences. She is associated to the Ollendorff Minerva Center for Vision and Image Sciences as part of the Andrew and Erna Viterbi Faculty of Electrical Engineering at the Technion - Israel Institute of Technology.

Her research interests focus on Imaging, Underwater Sensing, Computer Vision, Computational Photography, Oceanic Engineering.

The workshop entitled "The Mutual Shaping of Human-Robot Interaction", held in conjunction with IEEE International Symposium on Robot and Human Interactive Communication (IEEE RO-MAN 2017) in Lisbon, Portugal, August 28-31, 2017 is co-orgnaized by researchers from two TN-IIS partners. Please visit www.mutualshapinghri.com.

Workshop topic

The field of robotics has rapidly advanced over the last decades and shown great promises in different fields. After robots were introduced in industry decades ago, advancements in robotic systems have enabled them to increasingly enter and affect our everyday lives. Nowadays, we see robotic systems being introduced as assistants, team-mates, care-takers, and companions, in diverse contexts such as education, health and eldercare, the home, and in search and rescue. This development has started the discussion on the emotional, ethical and societal consequences of the increasing confrontations and interactions between humans and robots.

Studies in human-robot interaction have shown that, when robots enter different contexts of our everyday lives, they can influence and change that particular context beyond its intended use purpose alone. The term mutual shaping explains the detailed process of technological design suggesting that society and technology are not mutually exclusive to one another and, instead, influence and shape each other. Society changes as a direct result of the implementation of technology that has been created based on society’s wants and needs. The mutual shaping of technology and society approach focuses on analyzing how social and cultural factors influence the way technologies are designed, used, and evaluated, as well as how technologies affect our construction of social values and meanings.

The decisions made in the design, adoption, use, and evaluation process affect human’s attitudes towards, uses of, and even their conceptualizations of these (socially) interactive systems. Social norms, values and morals are both implicitly and explicitly intertwined with technologies, reinforcing or altering our beliefs and practices. Once a robot has entered a social environment, it will alter the distribution of responsibilities and roles within that environment, including how people act in that situation or use context. Accordingly, studies that show how use practices of robot systems and the social environment mutually shape each other, and what forms this mutual shaping process takes, is crucial for the future development of robots for broad societal use. This knowledge is required to inform the design and acceptance of new and existing robot systems.

Call for papers

The aim of this workshop is to inform the robotics community and its many stakeholders about lessons learned so far about the mutual shaping of robots and society. We will focus on how social factors affect whether people choose to use robots, and how robot design factors affect the social contexts in which robots are used. We welcome prospective participants to submit extended abstracts (max. 4 pages including references) covering any relevant topic contributing to the discussion on the mutual shaping effect(s) of robots and society. The goal is to discuss a wide variety of contributions from the many disciplines and approaches that intersect with the development and evaluation of robot systems (e.g. Human-Human Interaction, Human-Computer Interaction, Human-Robot Interaction, Human Factors User-Experience, engineering, computer sciences, (interactive) design, sociology, anthropology, psychology, etc.). We invite a diversity of topics from researchers and practitioners from a wide variety of fields who address strategies and lessons learned about mutual shaping of robots and society including, but not limited to:

  • Human-robot (non)use
  • Human-Robot interaction 
  • Mutual shaping of robots and society
  • Evaluation of robot applications and contexts of use
  • Socially intelligent robotics
  • Multimodal assessment technologies
  • Design of robotics systems
  • Social analysis of robotics
  • Social cognitive systems

The manuscripts should use the conference format. Please submit a PDF copy of your manuscript to s.benallouch@saxion.nl and maartje_de_graaf@brown.edu.

Timeline

June 1, 2017:  Submission deadline for workshop papers

June 22, 2017: Notification of acceptance

July 5, 2017: Camera-ready workshop papers deadline

July 10, 2017: Workshop program finalized

August 27 or September 1, 2017: Workshop day

August 28 – August 31, 2017: Main conference

 

Workshop organizers

Somaya Ben Allouch – Saxion University of Applied Sciences, The Netherlands

Maartje de Graaf – Brown University, USA

Selma Sabanovic – Indiana University, USA

Friederike Eyssel – Bielefeld University, Germany

CITEC researchers are developing a system together with Indiana University (USA) that enables robotic experiments to be replicated anywhere, regardless of location


The reliable and precise reproducibility of scientific experiments is crucial in research. In the natural sciences, such as biology, chemistry, and physics, it is an established practice to design an experiment so that it can be reproduced by other scientists. In robotics, however, reproducibility is still a challenging topic. Computer science doctoral researcher Florian Lier is developing in cooperation with the Central Lab Facilities and the Cognitive System Engineering research group an approach that facilitates the replication of software-intensive robotics experiments. The developed concept will be evaluated and improved in the DAAD-funded Thematic Network Interactive Intelligent Systems together with researchers at Indiana University. 


“In an experiment, when a robot takes an object in its hand and is supposed to pass it on to a person, various technical and methodical criteria must be considered if an experiment is to be reproduced at a different location,” says Florien Lier, who investigates the topic of the reproducibility of software-intensive robot experiments in his dissertation.
“Research findings in robotics are typically published as classic written articles in which hypotheses are proven or disproven using purely formal mathematical or data-driven statistical analyses,” says Lier. “Basic questions we ask ourselves not only in robotics, but in all computer-aided sciences include: how does the software used affect the analysis of the data? How much do the published findings depend on the software and hardware configuration used and the environment of the experiments? Can the same results also be attained using a form of the software that has only been slightly modified? In order to find answers to these questions, Lier is developing with his CITEC colleagues the Cognitive Interaction Toolkit (CITK).
The aim of the CITK is to achieve full reproducibility of a robotic experiment. In addition to the technical reproduction of the experimental system, the CITK provides a development process, which supports the transparent reproducibility of partial findings all the way through the final data set. This makes it easier to digitally share the basis for research findings, and to build further developments upon existing knowledge. Part of the toolkit includes a catalogue and various archives in which projects that have already been run are stored, and are available online to any researcher around the world, just as in a library.
“We have created step-by-step instructions that allow researchers to quickly and easily download the data and create an identical software environment – that is, a part of the experiment’s set up,” explains Florian Lier. Accordingly, a research group in the United States can, for instance, create the technical foundation for a robot experiment in the same way a group in Bielefeld can.
In addition to the technical aspects, there are also of course human aspects: The platform “jspsych” regulates what the study participants should do in an experiment. Phillip Lücking, who works in CITEC’s Central Labs, transferred this platform from the department of psychology at Indiana University to experimental set-ups in robotic research. The platform “jspsych” regulates the timing of the test procedure, or the display of stimuli, or for instance activates a certain type of robot behavior.
Together with Robert Goldstone and Selma Šabanović from Indiana University, the CITEC researchers currently planning to test their approach of reproducible researching in an upcoming experiment from psychology and human-machine. To do this, the researchers will make an experiment reproducible with the help of their toolkit. This will allow them to test whether the platform can be used publicly by international researchers. On 15 May 2017, Bielefeld researchers will travel to Indiana University to carry out a set of experiments with their colleagues in the USA.
In addition to the scientific value of reproducibility, the toolkit is also useful in this era of globalization and digital internationalization. Researchers will no longer have to travel to different countries to inspect experiments with robots on site. The toolkit already provides a so-called “online replay” for some selected experiments. With this, recorded data and the stages of the experiment can be played back with the click of a button. Researchers can then conveniently follow along the findings in their own Internet browser.
Currently, CITEC researchers are working on expanding the system to make it possible to locally start the systems and experiments gathered in the CITK toolkit. The experiments can then also be used by cooperation partners from other countries in a “remote lab”. In this way, the experiments can be replicated in the United States, Japan, Germany, or anywhere in the world. And what’s more: it is possible to observe an experimental set-up in Germany, or even perform that experiment, from the United States.

Contact
Florian Lier, Central Lab Facilities, flier@cit-ec.uni-bielefeld.de    
Dr.-Ing. Sebastian Wrede, Cognitive Systems Engineering
PD Dr.-Ing. Sven Wachsmuth, Central Lab Facilities
Cluster of Excellence Cognitive Interaction Technology (CITEC)
Bielefeld University


More information is available online at:
Platform of the Thematic Network Interactive Intelligent Systems
Cognitive Interaction Toolkit (CITK) research platform
Evaluation study of reproducing robot experiments

 

 

"On the Judicious Exploitation of Redundancy and Randomization for Performance Improvement"

Abstract:

Redundancy is well known as a way of tolerating faults in systems. However, it can also be used, sometimes in conjunction with randomization, to increase performance. In this talk I will start by providing some insights into forms of redundancy and their cost. Then, I illustrate this by way of a diverse set of examples from areas such as computer architecture, satellite communication and storage systems, mostly taken from my own research over the years.

Research interests:

Yitzhak "Tsahi" Birk heads the Parallel Systems Lab at the TN-IIS partner Technion in Haifa, Israel. His research interests include computer systems and subsystems, as well as communication networks. He is particularly interested in parallel and distributed architectures for information systems, including communication-intensive storage systems (e.g., multimedia servers) and satellite-based systems, with special attention to the true application requirements in each case. The judicious exploitation of redundancy for performance enhancement in these contexts has been the subject of much of his recent work. He is also engaged in research into various facets of processor architecture, attempting “cross fertilization” between his various areas of research.

This meeting is a crucial milestone for the Thematic Network and aims at elaborating more fields for research cooperation and exchange of especially young researchers between CITEC and IU in the future. Exciting joint projects between IU and CITEC are currently going on in the fields of Social Robotics and the Cognitive Interaction Toolkit. Our hosts, lead by Selma Sabanovic, plan to organize talks, discussions, bilateral meetings, and lab visits. Further, arrangements can be made matching your additional interests.

To find out more about the research and people at IU, please visit School of Informatics and Computing and Cognitive Science Program.

The Australian Centre for Robotic Vision organizes the annual summer school again in 2017. For more, please visit the official website of the event.

Among the participants are master students and PhD researchers from Bielefeld University (Julian Daberkow, Timo Michalski, Timo Korthals), who are supported by the German Academic Exchange Service (DAAD) and sponsored by the German Federal Ministry of Education and Research (BMBF).

Registration deadline: 27 January 2017

The DAAD has also funded the subsequent participation of Timo Korthals in the "Workshop on Reinforcement Learning in Robotics at QUT".

 

Reinforcement Learning (RL) has seen a surge of interest lately. Since its inception in the late 1990s it has been heralded as the most promising avenue to create autonomous systems. RL deals with the problem of sequential decision making in unknown (and often) stochastic and/or partially observable environments. There has been a lot of work recently on both empirical improvements (RL for robotics or other agents), as well a theoretical advances to push the boundaries of the field, such as the DeepMind Nature paper using visual information as state representation. Given the recent developments and the shared interest to create robots that can perceive their environment and adapt accordingly, we are planning the workshop. Focus will be on the application and potentials of (deep) Reinforcement Learning in Robotics and its overlap with other disciplines.

Organizer:

Dr. Jürgen Leitner

Australian Centre for Robotic Vision

Queensland University of Technology

Programme:

Day 1 Introduction to RL, Formulations for Robotics, Optimal Control vs RL, POMDP Modelling in Agrucultural Sensing

Day 2 Applications: Deep RL, Curiosity or where to get the reward from?, Inverse RL, Leanring Eye-hand Coordination

Day 3 Discussion of AMiRo platform, possible research projects and possible visits including student exchange.

Speaker and participants:

QUT: Ass. Prof. Shlomo Geva, Ass. Prof. Jason Ford, Dr. Niko Sünderhauf, Dr. Aaron Mcfayden, Adam Tow, Fangyi Zhang, Jenna Riseley

Bielefeld: Timo Korthals, Thomas Schöpping, Philipp Jünemann

 

The Neuromorphic Behaving Systems group is happy to announce that our Invited Speaker Dr. Chiara Bartolozzi from our TN-IIS partner Italian Institute of Technology (IIT) Genoa will give a talk titled "The neuromorphic approach to iCub." Dr. Bartolozzi will discuss the neuromorphic iCub featuring event-driven vision, as well as computation, touch and communication, showing that this approach is mature enough to deliver better performance in a state-of-the art humanoid robot for the perception of (and interaction with) dynamic scenes.

Robotics and AI hold the promise of permeating our daily lives in the near future. More specifically, robots of humanoid form can interact naturally with people as well as reuse the tools and environments already designed for human presence. Improving their perception and ability to react quickly to environmental stimuli is paramount for autonomy, needed for the effective deployment of robots in this scenario. This research line is about the design of cutting-edge, efficient technology for robot perception. This is obtained by combining hardware design and, consequently, by developing special algorithms for data processing. In particular, hardware is in the form of neuromorphic electronics for event-driven encoding of sensory signals, algorithms in the form of event-based signal processing.