Announcement

CFP – Special Issue: “Representations and Reasoning for Robotics”

Nicola Bellotto Announcement, publication, Uncategorized

Call for Papers

Special Issue of Robotics on “Representations and Reasoning for Robotics”

http://www.mdpi.com/journal/robotics/special_issues/reasoning-robotics

Deadline for manuscript submissions: 28 February 2015
As the field of robotics matures, the development of ever more intelligent robots becomes possible. However, robots deployed in homes, offices and other complex domains are faced with the formidable challenge of representing, revising and reasoning with incomplete domain knowledge about their capabilities, their environments, and how the former interacts with the latter.

Many algorithms have been developed for qualitatively and quantitatively representing and reasoning with knowledge and uncertainty. Unfortunately, research contributions in this area are fragmented, making it difficult for researchers with different expertise to share advances in their respective fields. The objective of this special issue is therefore to promote a deeper understanding of recent breakthroughs and challenges in knowledge representation and reasoning for robots. We are interested in efforts that integrate, or motivate an integration of algorithms for knowledge representation and/or commonsense reasoning, on one or more robots, in different application domains.

Topics of interest include (but are not limited to):

– Knowledge acquisition and representation
– Symbolic and probabilistic representations
– Reasoning with incomplete knowledge
– Interactive and cooperative decision-making
– Learning and symbol grounding
– Qualitative representations and reasoning

We particularly encourage the submission of papers that ground these topics in research areas such as robot perception, human–robot (and multirobot) collaboration, and robot planning.
Guest Editors

Dr. Nicola Bellotto
(University of Lincoln, UK)

Dr. Nick Hawes
(University of Birmingham, UK)

Dr. Mohan Sridharan
(The University of Auckland, New Zealand)

Prof. Daniele Nardi
(“Sapienza” Universita’ di Roma, Italy)
Submission

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are refereed through a peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Robotics is an international peer-reviewed Open Access quarterly journal published by MDPI.

Research presentation on co-evolution of humans and machines by Paul Granjon

gcielniak Announcement

PaulYou are kindly invited to the following research seminar which will take place on Friday, 29 November, 2-4pm at MC0024, MHT building.

Speaker: Paul Granjon, from Cardiff School of Art & Design, Cardiff Metropolitan University

Coy-B project and other robots for exploring the co-evolution of humans and machines

Paul Granjon is a performance and visual artist whose interest lies in the co-evolution of humans and machines, a subject he explores with self-made machines for live performance or exhibition. Granjon has produced since the late 1990s a collection of robots that include a set of Robotic Ears and Tail, several Automated Forests, a kicking automaton, a disco-dancing humanoid… His best-known creations to date are the Sexed Robots, a male and a female wheeled platforms that performed their cybernetic romance in the Welsh Pavilion at the Venice Biennale in 2005.

Motivated by a strong interest in the individual and social dynamics of techno-scientific progress, Granjon’s work provides a humorous yet critical comment on issues such as delegation to machines, digitisation of the social, technological body extension, sustainability, and also on the emergence of machinic life and the need for understanding the changing nature of contemporary artificial creatures. These two notions are at the core of Granjon’s ongoing Coy-B project.

A performance art experiment in human-machine interaction loosely based on Joseph Beuys’ performance I Like America and America Likes Me (1974) where the artist shared a gallery space with a wild coyote, the Coy-B project will be a performance for an advanced robot and a human in a shared territory. Diametrically opposed to the coyote who was a representative of instinct, a wild natural being, the Coy-B robot will represent wild machinic life. The performance aims to offer a platform for observing the relation between a human and an intelligent machines at a time when the boundaries between living and artificial are blurred.

The talk will feature examples of Granjon’s past work, references from art, science and technology, and a detailed presentation of the Coy-B project.

Paul Granjon’s website: www.zprod.org

Sebastian Wrede at Research Seminar

Marc Hanheide Announcement

Everybody in Lincoln is invited to learn about some exciting research:

 
Time/Date: 4pm, Tuesday, 1 Oct 2013

Venue: MB1015, Main Admin Building
Speaker:  Dr. Sebastian Wrede, Cognitive Systems Engineering, CoR-Lab, Bielefeld University

Title: Kinesthetic Teaching of Redundant Robots in Task and Configuration Space
Abstract: The recent advent of compliant and kinematically redundant robots poses new research challenges for human-robot interaction. While these robots provide high flexibility for the realization of complex applications, the gained flexibility generates the need for additional modeling steps and the definition of criteria for redundancy resolution constraining the robot’s movement generation. The explicit modeling of such criteria usually require experts to adapt the robot’s movement generation subsystem. A typical way of dealing with this configuration challenge is to utilize kinesthetic teaching and guide the robot to implicitly model the specific constraints in task and configuration space. However, in this presentation we report on experiments showing that current programming-by-demonstration approaches are not efficient for kinesthetic teaching of redundant robots and typical teach-in procedures are too complex for novice users. In order to enable non-experts to master the configuration and programming of a redundant robot in the presence of non-trivial constraints such as confined spaces, the talk presents a new interaction scheme combining kinesthetic teaching and learning within an integrated system architecture. The approach was evaluated in a user study with 49 industrial workers in a medium-sized manufacturing company.  Results show that the interaction concepts implemented on a KUKA Lightweight Robot IV are easy to handle for novice users, demonstrate the feasibility of kinesthetic teaching for implicit constraint modeling in configuration space and yield significantly improved performance for the teach-in of trajectories in task space.

Video