About me
I am a senior researcher in the Talking
Robots group of DFKI's
Language Technology Lab.
My research interests include linguistic aspects of spatial cognition for autonomous robots and
situated human-robot interaction, with a focus on natural-language generation for transparency in
autonomous behavior. Currently, my research is sponsored by the EU-funded FP7 research projects
CogX and
NIFTi. Before that I was part of the FP6 project
CoSy. I studied
Computational Linguistics at
Saarland University in Saarbrücken, Germany,
where I obtained a degree as Diplom-Linguist (Computerlinguistik), and consequently pursued
a PhD in the same field.
April 2012
Our Special Issue on
Expectations, Intentions, and Actions
in Human-Robot Interaction in the
International
Journal of Social Robotics has been released. Thanks to everyone involved!
December 2011
My PhD thesis
has been published in the series
"Saarbrücken Dissertations in Computational Linguistics and Language Technology!"
It can be ordered using the
online order form.
December 2010
I successfully defended my PhD. Very special thanks to my first and second reviewers Prof. Dr.
Hans Uszkoreit and Prof. Dr. Massimo Poesio, as well as to my advisor Dr. Geert-Jan Kruijff, and the
other two members of my committee Prof. Dr. Erich Steiner and Prof. Dr. Elke Teich.
To appear
Geert-Jan M. Kruijff, Miroslav Janicek, and Hendrik Zender (2012).
Situated Communication for Joint Activity in Human-Robot Teams.
IEEE Intelligent Systems. To appear.
2012
Marc Hanheide, Manja Lohse, and Hendrik Zender (2012).
Expectations, Intentions, and Actions in Human-Robot Interaction.
International Journal of Social Robotics, Special Issue "Expectations, Intentions & Actions".
Vol. 4, Issue 2. pp. 107--108. Springer Verlag, Berlin/Heidelberg, Germany. April 2012.
[Abstract]
[BibTeX]
[SpringerLink]
[DOI]
Human-robot interaction is becoming increasingly complex through the growing number of abilities,
both cognitive and physical, available to today's robots. At the same time, interaction is still
often difficult because the users do not understand the robots' internal states, expectations,
intentions, and actions. Vice versa, robots lack understanding of the users' expectations,
intentions, actions, and social signals. Each of the seven articles in this issue highlights
different aspects around the central theme of expectations, intentions, and actions in human-robot
interaction. The topics covered range from recognition of verbal and non-verbal cues of intentions
and expectations, to verbalisation and presentation techniques that make internal processing of the
robot accessible to the human.
@article{hanheide/etal:2012-soro_editorial,
author = {Hanheide, Marc and Lohse, Manja and Zender, Hendrik},
title = {Expectations, Intentions, and Actions in Human-Robot Interaction},
journal = {International Journal of Social Robotics},
volume = {4},
number = {2},
address = {Berlin/Heidelberg, Germany},
pages = {107--108},
doi = {10.1007/s12369-012-0139-x},
publisher = {Springer Verlag},
month = {April},
year = {2012}}
Shanker Keshavdas, Hendrik Zender, Geert-Jan Kruijff, Ming Liu, and Francis Colas (2012).
Functional Mapping: Spatial Inferencing to aid Human-Robot Rescue Efforts in Unstructured
Disaster Environments.
Proceedings of the 2012 AAAI Spring Symposium on Designing Intelligent Robots.
Menlo Park, CA, USA. March 2012.
[Abstract]
[BibTeX]
In this paper we examine the case of a mobile robot that is part of a human-robot urban search and
rescue (USAR) team. During USAR scenarios, we would like the robot to have a geometrical-functional
understanding of space, using which it can infer where to perform planned tasks in a manner that
mimics human behavior. We assess the situation awareness of rescue workers during a simulated USAR
scenario and use this as an empirical basis to build our robot's spatial model. Based upon this
spatial model, we present functional mapping as an approach to identify regions in the USAR
environment where planned tasks are likely to be optimally achievable. The system is deployed and
evaluated in a simulated rescue scenario.
@article{keshavdas/etal:2012-aaaisss,
author = {Keshavdas, Shanker and Zender, Hendrik and Kruijff, Geert-Jan and Liu, Ming and
Colas, Francis},
title = {Functional Mapping: Spatial Inferencing to Aid Human-Robot Rescue Efforts
in Unstructured Disaster Environments},
booktitle = {Proceedings of the 2012 AAAI Spring Symposium on Designing Intelligent Robots},
year = {2012}
month = {March},
publisher = {AAAI Press},
address = {Menlo Park, CA, USA}}
2011
Hendrik Zender (2011).
Situated Production and Understanding of Verbal References to Entities in Large-Scale Space.
Volume 36 of
Saarbrücken Dissertations in Computational Linguistics and Language Technology.
German Research Center for Artificial Intelligence and Saarland University, Saarbrücken, Germany, 12/2011.
[Abstract]
[BibTeX]
The work presented in this thesis addresses the fundamental questions of how machines, such as robots
and other autonomous agents, can acquire a mental representation of their environment that allows them
to (a) act and navigate in it, and (b) communicate about it with humans in natural language.
We specifically investigate representations of structured environments that cannot be apprehended as
a perceptual whole (i.e., large-scale space). This comprises, for instance, indoor domestic environments,
or building ensembles. By that, the presented work goes beyond situated natural language interaction
about an agent's immediate surroundings (i.e., small-scale space), such as table-tops or single room spaces.
Situated communication about entities – that is, things, places, properties, and events –
in large-scale space requires the interlocutors to draw attention to entities that are not currently
observable, and to comprehend which remote places and things are being talked about.
We furthermore show how such representations that can be used for spoken interaction with human users
also endow autonomous agents with skills for context-aware planning and execution of actions in
structured environments that are made by and for humans. To this end, the presented spatial models
have been implemented and deployed in integrated systems for intelligent mobile robots.
We then present an approach for natural language generation and understanding that makes use of the
acquired spatial models. It allows an agent to successfully generate and resolve natural language
expressions that refer to entities in large-scale space. The approach is backed by observations from
an empirical spoken language production experiment. The thesis concludes with a discussion of
ongoing work to transfer the models made for intelligent mobile robots to autonomous virtual agents
that act in an online virtual 3D world.
@book{zender:2011-phd,
author = {Zender, Hendrik},
title = {Situated Production and Understanding of Verbal References to Entities
in Large-Scale Space},
series = {Saarbr\"{u}cken Dissertations in Computational Linguistics
and Language Technology},
volume = {36},
publisher = {German Research Center for Artificial Intelligence and Saarland University},
address = {Saarbr\"{u}cken, Germany},
year = {2011},
note = {hardcopies available here; ISBN 978-3-933218-35-3}}
Mario Gianni, Panagiotis Papadakis, Fiora Pirri, Ming Liu, Francois Pomerleau, Francis Colas,
Karel Zimmermann, Tomas Svoboda, Tomas Petricek, Geert Jan Kruijff, Harmish Khambhaita,
and Hendrik Zender (2011).
A Unified Framework for Planning and Execution-Monitoring of Mobile Robots.
In Sanem Sariel-Talay, Stephen F. Smith, Nilufer Onder (eds.):
Proceedings of the AAAI-11 Workshop on Automated Action Planning for Autonomous Mobile Robots
(PAMR). San Francisco, CA, United States, August 2011.
[Abstract]
[BibTeX]
We present an original integration of high level planning and execution with incoming perceptual
information from vision, SLAM, topological map segmentation and dialogue. The task of the robot
system, implementing the integrated model, is to explore unknown areas and report detected objects
to an operator, by speaking loudly. The knowledge base of the planner maintains a graph-based
representation of the metric map that is dynamically constructed via an unsupervised topological
segmentation method, and augmented with information about the type and position of detected objects,
within the map, such as cars or containers. According to this knowledge the cognitive robot can
infer strategies in so generating parametric plans that are instantiated from the perceptual
processes. Finally, a model-based approach for the execution and control of the robot system is
proposed to monitor, concurrently, the low level status of the system and the execution of the
activities, in order to achieve the goal, instructed by the operator.
@inproceedings{gianni/etal:2011-pamr,
author = {Gianni, Mario and Papadakis, Panagiotis and Pirri, Fiora and Liu, Ming and
Pomerleau, Francois and Colas, Francis and Zimmermann, Karel and
Svoboda, Tomas and Petricek, Tomas and Kruijff, Geert-Jan and
Khambhaita, Harmish and Zender, Hendrik},
title = {A Unified Framework for Planning and Execution-Monitoring of Mobile Robots},
booktitle = {Proceedings of the AAAI-11 Workshop on Automated Action Planning for
Autonomous Mobile Robots (PAMR).}
address = {San Francisco, CA, USA},
month = {August},
year = {2011}}
Marc Hanheide, Charles Gretton, Richard Dearden, Nick Hawes, Jeremy Wyatt, Andrzej Pronobis,
Alper Aydemir, Moritz Göbelbecker, and Hendrik Zender (2011).
Exploiting Probabilistic Knowledge under Uncertain Sensing for Efficient Robot Behaviour.
In Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence
(IJCAI-11). Barcelona, Catalonia, Spain, July 2011.
[Abstract]
[BibTeX]
Robots must perform tasks efficiently and reliably while acting under uncertainty. One way to
achieve efficiency is to give the robot common-sense knowledge about the structure of the world.
Reliable robot behaviour can be achieved by modelling the uncertainty in the world probabilistically.
We present a robot system that combines these two approaches and demonstrate the improvements in
efficiency and reliability that result. Our first contribution is a probabilistic relational model
integrating common-sense knowledge about the world in general, with observations of a particular
environment. Our second contribution is a continual planning system which is able to plan in the
large problems posed by that model, by automatically switching between decision-theoretic and
classical procedures. We evaluate our system on object search tasks in two different real-world
indoor environments. By reasoning about the trade-offs between possible courses of action with
different informational effects, and exploiting the cues and general structures of those
environments, our robot is able to consistently demonstrate efficient and reliable goal-directed
behaviour.
@inproceedings{hanheide/etal:2011-ijcai,
author = {Hanheide, Marc and Gretton, Charles and Dearden, Richard and Hawes, Nick and
Wyatt, Jeremy and Pronobis, Andrzej and Aydemir, Alper and G\"{o}belbecker,
Moritz and Zender, Hendrik},
title = {Exploiting Probabilistic Knowledge under Uncertain Sensing for Efficient
Robot Behaviour},
booktitle = {Proceedings of the Twenty-Second International Joint Conference on
Artificial Intelligence ({IJCAI-11})},
address = {Barcelona, Catalonia, Spain},
month = {July},
year = {2011}}
Nick Hawes, Marc Hanheide, Jack Hargreaves, Ben Page, Hendrik Zender, and Patric Jensfelt (2011).
Home Alone: Autonomous Extension and Correction of Spatial Representations.
In Proceedings of the 2011 IEEE International Conference on Robotics and Automation (ICRA 2011).
Shanghai, China, May 2011.
[Abstract]
[BibTeX]
[PDF]
In this paper we present an account of the problems faced by a mobile robot given an incomplete tour
of an unknown environment, and introduce a collection of techniques which can generate successful
behaviour even in the presence of such problems. Underlying our approach is the principle that an
autonomous system must be motivated to act to gather new knowledge, and to validate and correct
existing knowledge. This principle is embodied in Dora, a mobile robot which features the
aforementioned techniques: shared representations, non-monotonic reasoning, and goal generation and
management. To demonstrate how well this collection of techniques work in real-world situations we
present a comprehensive analysis of the Dora system's performance over multiple tours in an indoor
environment. In this analysis Dora successfully completed 18 of 21 attempted runs, with all but 3 of
these successes requiring one or more of the integrated techniques to recover from problems.
@inproceedings{hawes/etal:2011-icra,
author = {Hawes, Nick and Hanheide, Marc and Hargreaves, Jack and Page, Ben and
Zender, Hendrik and Jensfelt, Patric},
title = {Home Alone: Autonomous Extension and Correction of Spatial Representations},
booktitle = {Proceedings of the 2011 {IEEE} International Conference on Robotics and
Automation ({ICRA 2011})},
address = {Shanghai, China},
organization = {IEEE},
month = {May},
year = {2011}}
2010
Jeremy L. Wyatt, Alper Aydemir, Michael Brenner, Marc Hanheide, Nick Hawes, Patric Jensfelt,
Matej Kristan, Geert-Jan M. Kruijff, Pierre Lison, Andrzej Pronobis, Kristoffer Sjöö,
Danijel Skočaj, Alen Vrecko, Hendrik Zender, and Michael Zillich (2010).
Self-Understanding and Self-Extension: A systems and representational approach.
In IEEE Transactions on Autonomous Mental Development (TAMD).
Vol. 2, Issue 4, IEEE, December 2010.
[Abstract]
[BibTeX]
[DOI]
There are many different approaches to building a system that can engage in autonomous mental
development. In this paper we present an approach based on what we term self-understanding, by which
we mean the use of explicit representation of and reasoning about what a system does and doesn't
know, and how that understanding changes under action. We present a coherent architecture and a set
of representations used in two robot systems that exhibit a limited degree of autonomous mental
development, what we term self-extension. The contributions include: representations of gaps and
uncertainty for specific kinds of knowledge, and a motivational and planning system for setting and
achieving learning goals.
@article{wyatt/etal:2010-tamd,
author = {Wyatt, Jeremy L. and Aydemir, Alper and Brenner, Michael and Hanheide, Marc
and Hawes, Nick and Jensfelt, Patric and Kristan, Matej
and Kruijff, Geert-Jan M. and Lison, Pierre and Pronobis, Andrzej
and Sj\"{o}\"{o}, Kristoffer and Sko\v{c}aj, Danijel and Vrecko, Alen
and Zender, Hendrik and Zillich, Michael},
title = {Self-Understanding and Self-Extension: A systems and representational
approach},
journal = {IEEE Transactions on Autonomous Mental Development (TAMD)},
volume = {2},
number = {4},
pages = {282-303},
organization = {IEEE},
url = {http://dx.doi.org/10.1109/TAMD.2010.2090149},
month = {December},
year = {2010}}
Marc Hanheide, Nick Hawes, Jeremy L. Wyatt, Moritz Göbelbecker, Michael Brenner, Kristoffer
Sjöö, Alper Aydemir, Patric Jensfelt, Hendrik Zender, and Geert-Jan M. Kruijff (2010).
A Framework for Goal Generation and Management.
In Proceedings of the AAAI Workshop on Goal-Directed Autonomy.
Atlanta, GA, USA, July 2010.
[Abstract]
[BibTeX]
[PDF]
Goal-directed behaviour is often viewed as an essential characteristic of an intelligent system, but
mechanisms to generate and manage goals are often overlooked. This paper addresses this by
presenting a framework for autonomous goal generation and selection. The framework has been
implemented as part of an intelligent mobile robot capable of exploring unknown space and
determining the category of rooms autonomously. We demonstrate the efficacy of our approach by
comparing the performance of two versions of our integrated system: one with the framework, the
other without. This investigation leads us conclude that such a framework is desirable for an
integrated intelligent system because it reduces the complexity of the problems that must be solved
by other behaviour-generation mechanisms, it makes goal-directed behaviour more robust in the face
of a dynamic and unpredictable environment, and it provides an entry point for domain-specific
knowledge in a more general system.
@inproceedings{hanheide/etal:2010-fgg,
author = {Hanheide, Marc and Hawes, Nick and Wyatt, Jeremy L. and G{\"o}belbecker, Moritz
and Brenner, Michael and Sj\"{o}\"{o}, Kristoffer and Aydemir, Alper and
Jensfelt, Patric and Zender, Hendrik and Kruijff, Geert-Jan M.},
title = {A Framework for Goal Generation and Management},
booktitle = {Proceedings of the {AAAI} Workshop on Goal-Directed Autonomy},
address = {Atlanta, GA, USA},
organization = {AAAI},
month = {July},
year = {2010}}
Hendrik Zender, Christopher Koppermann, Fai Greeve, and Geert-Jan M. Kruijff (2010).
Anchor-Progression in Spatially Situated Discourse: a Production Experiment.
In Proceedings of the Sixth International Natural Language Generation Conference (INLG 2010).
Trim, Co. Meath, Ireland, July 2010.
[Abstract]
[BibTeX]
[PDF]
The paper presents two models for producing and understanding situationally appropriate referring
expressions (REs) during a discourse about large-scale space. The models are evaluated against an
empirical production experiment.
@inproceedings{zender/etal:2010-inlg,
author = {Zender, Hendrik and Koppermann, Christopher and Greeve, Fai
and Kruijff, Geert-Jan M.},
title = {Anchor-Progression in Spatially Situated Discourse: a Production Experiment},
booktitle = {Proceedings of the Sixth International Natural Language Generation Conference
({INLG 2010})},
pages = {209--213},
address = {Trim, Co. Meath, Ireland},
organization = {Association for Computational Linguistics},
month = {July},
year = {2010}}
Nick Hawes and Marc Hanheide and Kristoffer Sjöö and Alper Aydemir and Patric
Jensfelt and Moritz Göbelbecker and Michael Brenner and Hendrik Zender and Pierre
Lison and Ivana Kruijff-Korbayová and Geert-Jan Kruijff and Michael Zillich (2010).
Dora The Explorer: A Motivated Robot.
In Proceedings of the 9th International Conference on Autonomous Agents and Multiagent
Systems (AAMAS '10).
Toronto, ON, Canada. May 2010.
[Abstract]
[BibTeX]
Dora the Explorer is a mobile robot with a sense of curiosity and a drive to explore its
world. Given an incomplete tour of an indoor environment, Dora is driven by internal
motivations to probe the gaps in her spatial knowledge. She actively explores regions of
space which she hasn't previously visited but which she expects will lead her to further
unexplored space. She will also attempt to determine the categories of rooms through
active visual search for functionally important objects, and through ontology-driven
inference on the results of this search.
@inproceedings{hawes/etal:2010-aamas,
author = {Hawes, Nick and Hanheide, Marc and Sj\"{o}\"{o}, Kristoffer and
Aydemir, Alper and Jensfelt, Patric and G\"{o}belbecker, Moritz and
Brenner, Michael and Zender, Hendrik and Lison, Pierre and
Kruijff-Korbayov\'{a}, Ivana and Kruijff, Geert-Jan M. and Zillich, Michael},
title = {Dora The Explorer: A Motivated Robot},
booktitle = {Proceedings of the 9th International Conference on Autonomous Agents and
Multiagent Systems (AAMAS '10)},
pages = {1617--1618},
address = {Toronto, ON, Canada},
month = {May},
year = {2010}}
Marc Hanheide and Hendrik Zender (2010).
Proceedings of the ICRA 2010 Workshop on Interactive Communication for Autonomous Intelligent
Robots (ICAIR).
Anchorage, AK, USA. May 2010.
[BibTeX]
[PDF]
[Workshop Homepage]
@proceedings{hanheide/zender:2010-icairproc,
editor = {Hanheide, Marc and Zender, Hendrik},
title = {Proceedings of the {ICRA} 2010 Workshop on Interactive Communication for
Autonomous Intelligent Robots ({ICAIR})},
address = {Anchorage, AK, USA},
month = {May},
year = {2010}}
Andrzej Pronobis, Patric Jensfelt, Kristoffer Sjöö, Hendrik Zender,
Geert-Jan M. Kruijff, Óscar Martínez Mozos, and Wolfram Burgard (2010).
Semantic Modelling of Space.
In Henrik Iskov Christensen, Geert-Jan M. Kruijff, and Jeremy L. Wyatt, editors,
Cognitive Systems, volume 8 of Cognitive Systems Monographs,
chapter 5.
Springer Verlag, Berlin/Heidelberg, Germany, April 2010.
[BibTeX]
[Springer]
[CoSy Book Website]
@incollection{cosybook:space,
author = {Pronobis, Andrzej and Jensfelt, Patric and Sj\"{o}\"{o}, Kristoffer and
Zender, Hendrik and Kruijff, Geert-Jan M. and Mozos, \'{O}scar Mart\'{i}nez
and Burgard, Wolfram},
title = {Semantic Modelling of Space},
editor = {Christensen, Henrik Iskov and Kruijff, Geert-Jan M. and Wyatt, Jeremy L.},
booktitle = {Cognitive Systems},
chapter = {5},
pages = {165--221},
series = {Cognitive Systems Monographs},
publisher = {Springer Verlag},
address = {Berlin/Heidelberg, Germany},
volume = {8},
year = {2010}}
Geert-Jan M. Kruijff, Pierre Lison, Trevor Benjamin, Henrik Jacobsson, Hendrik
Zender,and Ivana Kruijff-Korbayová (2010).
Situated Dialogue Processing for Human-Robot Interaction.
In Henrik Iskov Christensen, Geert-Jan M. Kruijff, and Jeremy L. Wyatt, editors,
Cognitive Systems, volume 8 of Cognitive Systems Monographs,
chapter 8.
Springer Verlag, Berlin/Heidelberg, Germany, April 2010.
[BibTeX]
[Springer]
[CoSy Book Website]
@incollection{cosybook:dialogue,
author = {Kruijff, Geert-Jan M. and Lison, Pierre and Benjamin, Trevor and Jacobsson,
Henrik and Zender, Hendrik and Kruijff-Korbayov\'{a}, Ivana},
title = {Situated Dialogue Processing for Human-Robot Interaction},
editor = {Christensen, Henrik Iskov and Kruijff, Geert-Jan M. and Wyatt, Jeremy L.},
booktitle = {Cognitive Systems},
chapter = {8},
pages = {311--364},
series = {Cognitive Systems Monographs},
publisher = {Springer Verlag},
address = {Berlin/Heidelberg, Germany},
volume = {8},
year = {2010}}
Kristoffer Sjöö, Hendrik Zender, Patric Jensfelt, Geert-Jan M. Kruijff,
Andrzej Pronobis, Nick Hawes, and Michael Brenner (2010).
The Explorer System.
In Henrik Iskov Christensen, Geert-Jan M. Kruijff, and Jeremy L. Wyatt, editors,
Cognitive Systems, volume 8 of Cognitive Systems Monographs,
chapter 10.
Springer Verlag, Berlin/Heidelberg, Germany, April 2010.
[BibTeX]
[Springer]
[CoSy Book Website]
@incollection{cosybook:explorer,
author = {Sj\"{o}\"{o}, Kristoffer and Zender, Hendrik and Jensfelt, Patric and Kruijff,
Geert-Jan M. and Pronobis, Andrzej and Hawes, Nick and Brenner, Michael},
title = {The {Explorer} System},
editor = {Christensen, Henrik Iskov and Kruijff, Geert-Jan M. and Wyatt, Jeremy L.},
booktitle = {Cognitive Systems},
chapter = {10},
pages = {395--421},
series = {Cognitive Systems Monographs},
publisher = {Springer Verlag},
address = {Berlin/Heidelberg, Germany},
volume = {8},
year = {2010}}
Alper Aydemir, Michael Brenner, Moritz Göbelbecker, Marc Hanheide, Nick Hawes, Patric
Jensfelt, Geert-Jan M. Kruijff, Ivana Kruijff-Korbayová, Pierre Lison, Kristoffer
Sjöö, Jeremy Wyatt, Hendrik Zender, and Michael Zillich (2010).
Dora The Explorer: A Mobile Robot Motivated by Curiosity
Proceedings of the 4th International Conference on Cognitive Systems (CogSys 2010).
Zürich, Switzerland. January 2010.
[Poster PDF]
2009
Hendrik Zender, Geert-Jan M. Kruijff, and Ivana Kruijff-Korbayová (2009b).
Situated Resolution and Generation of Spatial Referring Expressions for Robotic Assistants.
Twenty-first International Joint Conference on Artificial Intelligence (IJCAI-09).
AAAI. Pasadena, CA, USA. July 2009.
[Abstract]
[BibTeX]
[PDF]
In this paper we present an approach to the task of generating and
resolving referring expressions (REs) for conversational mobile robots.
It is based on a spatial knowledge base encompassing both robot- and
human-centric representations. Existing algorithms for the generation
of referring expressions (GRE) try to find a description that uniquely
identifies the referent with respect to other entities
that are in the current context. Mobile robots, however,
act in large-scale space, that is environments that are larger than
what can be perceived at a glance, e.g. an office building with
different floors, each containing several rooms and
objects. One challenge when referring to elsewhere is thus to
include enough information so that the interlocutors can extend
their context appropriately. We address this challenge with a method
for context construction that can be used for both generating and resolving
REs – two previously disjoint aspects. Our approach is embedded in a
bi-directional framework for natural language processing for robots.
@inproceedings{zender/etal:2009-ijcai,
author = {Hendrik Zender and Geert-Jan M. Kruijff and Ivana Kruijff-Korbayov\'{a}},
title = {Situated Resolution and Generation of Spatial Referring Expressions
for Robotic Assistants},
booktitle = {Proceedings of the Twenty-First International Joint Conference on
Artificial Intelligence (IJCAI-09)},
pages = {1604--1609},
address = {Pasadena, CA, USA},
month = {July},
year = {2009},
url = {http://www.dfki.de/~zender/publications/zender_etal09-ijcai.pdf}}
Nick Hawes, Hendrik Zender, Kristoffer Sjöö, Michael Brenner, Geert-Jan M. Kruijff, and Patric Jensfelt (2009).
Planning and Acting with an Integrated Sense of Space
IJCAI Workshop on Hybrid Control of Autonomous Systems (HYCAS).
Pasadena, CA, USA. July 2009.
[Abstract]
[BibTeX]
[PDF]
The paper describes PECAS, an architecture for intelligent systems,
and its application in the Explorer, an interactive mobile robot.
PECAS is a new architectural combination of information fusion and
continual planning. PECAS plans, integrates and monitors the asynchronous
flow of information between multiple concurrent systems. Information fusion
provides a suitable intermediary to robustly couple the various reactive
and deliberative forms of processing used concurrently in the Explorer.
The Explorer instantiates PECAS around a hybrid spatial model combining SLAM,
visual search, and conceptual inference. This paper describes the
elements of this model, and demonstrates on an implemented scenario how PECAS provides
means for flexible control.
@inproceedings{hawes/etal:2009-hycas,
author = {Nick Hawes and Hendrik Zender and Kristoffer Sj\"{o}\"{o} and Michael Brenner
and Geert-Jan M. Kruijff and Patric Jensfelt},
title = {Planning and Acting with an Integrated Sense of Space},
booktitle = {Proceedings of the 1st International Workshop on Hybrid Control of Autonomous
Systems -- Integrating Learning, Deliberation and Reactive Control (HYCAS)},
pages = {25--32},
address = {Pasadena, CA, USA},
month = {July},
year = {2009},
url = {http://www.dfki.de/~zender/publications/hawes_etal09-hycas.pdf}}
Hendrik Zender, Geert-Jan M. Kruijff, and Ivana Kruijff-Korbayová (2009a).
A Situated Context Model for Resolution and Generation of Referring Expressions
12th European Workshop on Natural Language Generation (ENLG 2009).
pp. 126--129. ACL. Athens, Greece. March 2009.
[Abstract]
[BibTeX]
[PDF]
[Poster PDF]
The background for this paper is the aim to build robotic assistants that
can naturally interact with humans. One prerequisite for this is that
the robot can correctly identify objects or places a user refers to, and
produce comprehensible references itself. As robots typically act in
environments that are larger than what is immediately perceivable, the
problem arises how to identify the appropriate context, against which to
resolve or produce a referring expression (RE). Existing algorithms for
generating REs generally by-pass this problem by assuming a given context.
In this paper, we explicitly address this problem, proposing a method for
context determination in large-scale space. We show how it can be applied
both for resolving and producing REs.
@inproceedings{zender/etal:2009-enlg,
author = {Hendrik Zender and Geert-Jan M. Kruijff and Ivana Kruijff-Korbayov\'{a}},
title = {A Situated Context Model for Resolution and Generation of Referring
Expressions},
booktitle = {Proceedings of the 12th European Workshop on Natural Language Generation
(ENLG 2009)},
address = {Athens, Greece},
month = {March},
year = {2009},
publisher = {Association for Computational Linguistics},
pages = {126--129},
url = {http://www.aclweb.org/anthology/W09-0622}}
2008
Hendrik Zender, Óscar Martínez Mozos, Patric Jensfelt,
Geert-Jan M. Kruijff, and Wolfram Burgard (2008).
Conceptual Spatial Representations for Indoor Mobile Robots
Robotics and Autonomous Systems, Special Issue "From Sensors to Human Spatial Concepts".
Vol. 56, Issue 6. pp. 493--502. Elsevier. June 2008.
[Abstract]
[BibTeX]
[Author's manuscript PDF]
[DOI]
We present an approach for creating conceptual representations of human-made
indoor environments using mobile robots. The concepts refer to spatial and
functional properties of typical indoor environments. Following findings in
cognitive psychology, our model is composed of layers representing maps at
different levels of abstraction. The complete system is integrated in a mobile
robot endowed with laser and vision sensors for place and ob ject recognition.
The system also incorporates a linguistic framework that actively supports the
map acquisition process, and which is used for situated dialogue. Finally,
we discuss the capabilities of the integrated system.
@article{zender/etal:2008-ras_fs2hsc,
author = {Hendrik Zender and \'{O}scar Mart\'{i}nez Mozos and
Patric Jensfelt and Geert-Jan M. Kruijff and Wolfram Burgard},
title = {Conceptual Spatial Representations for Indoor Mobile Robots},
journal = {Robotics and Autonomous Systems},
publisher = {Elsevier},
doi = {10.1016/j.robot.2008.03.007},
volume = {56},
number = {6},
pages = {493--502},
month = {June},
year = {2008}}
Geert-Jan M. Kruijff and Hendrik Zender and Marc Hanheide and Britta Wrede (2008).
Proceedings of the ICRA 2008 Workshop: Social Interaction with Intelligent Indoor Robots (SI3R)
Pasadena, CA, USA. May 2008.
[Abstract]
[BibTeX]
[PDF]
[Workshop Homepage]
Robots are moving from the factories into our homes. Today, we have the Roomba.
Tomorrow, in 2010, industry aims to give us the first commercial humanoids.
Bringing robots as assistants into homes, offices, and shopping malls presents
serious challenges to human-robot interaction. Robots will need to assist untrained
users. Robots will need to interact with people in environments that are designed
for, and populated by, humans. This workshop focuses on how robotic systems can be
designed such as to meet these challenges. Make robots adapt to
the environment. Make robots socially acceptable. Make robots fit into the environment,
without the environment needing to be made to fit them.
@proceedings{si3r-icra-proc:2008,
editor = {Geert-Jan M. Kruijff and Hendrik Zender and Marc Hanheide and Britta Wrede},
title = {Proceedings of the ICRA 2008 Workshop:
Social Interaction with Intelligent Indoor Robots (SI3R)},
address = {Pasadena, CA, USA},
month = {May},
year = {2008}}
2007
Hendrik Zender and Geert-Jan M. Kruijff (2007).
Towards Generating Referring Expressions in a Mobile Robot Scenario
Language and Robots: Proceedings from the Symposium (LangRo'2007).
pp. 101--106.
Aveiro, Portugal. December 2007.
[Abstract]
[BibTeX]
[PDF]
This paper describes an approach towards generating
referring expressions that identify and distinguish spatial entities in
large-scale space, e.g. in an office environment, for autonomous mobile
robots. In such a scenario a dialogue is often about things and places
outside the current perceptual fields of the interlocutors. One of the
challenges therefore lies in determining an appropriate dialogue
context. Other important issues are to have adequate models of both the
large-scale spatial environment and of the user's knowledge.
@inproceedings{zender/kruijff:2007-langro,
author = {Hendrik Zender and Geert-Jan M. Kruijff},
title = {Towards Generating Referring Expressions in a Mobile Robot Scenario},
booktitle = {Language and Robots: Proceedings of the Symposium},
pages = {101--106},
address = {Aveiro, Portugal},
month = {December},
year = {2007}}
Óscar Martínez Mozos, Patric Jensfelt, Hendrik Zender,
Geert-Jan M. Kruijff, and Wolfram Burgard (2007b).
An Integrated System for Conceptual Spatial Representations
of Indoor Environments for Mobile Robots
Proceedings of the IROS 2007 Workshop: From Sensors to Human Spatial Concepts (FS2HSC).
pp. 25--32.
San Diego, CA, USA. November 2007.
[Abstract]
[BibTeX]
[PDF]
We present an integrated approach for creating conceptual
representations of human-made environments using mobile robots. The concepts
represent spatial and functional properties of typical indoor environments. Our
model is composed of layers which represent maps at different levels of
abstraction. The complete system was integrated in a service robot which
is endowed with laser and vision sensors for place and object recognition.
It also incorporates a linguistic framework that actively supports the map
acquisition process and is used for situated dialogue.
In the experiments we show how the robot acquires the conceptual information
and how it is used for situational and functional awareness.
@inproceedings{mozos/etal:2007-irosws,
author = {\'{O}scar Mart\'{i}nez Mozos and Patric Jensfelt and Hendrik Zender
and Geert-Jan M. Kruijff and Wolfram Burgard},
title = {An Integrated System for Conceptual Spatial
Representations of Indoor Environments for Mobile Robots},
booktitle = {Proceedings of the IROS 2007 Workshop:
From Sensors to Human Spatial Concepts (FS2HSC)},
pages = {25--32},
address = {San Diego, CA, USA},
month = {November},
year = {2007}}
Hendrik Zender, Patric Jensfelt, and Geert-Jan M. Kruijff (2007).
Human- and Situation-Aware People Following
Proceedings of the 16th IEEE International Symposium on Robot and Human
Interactive Communication (RO-MAN 2007).
pp. 1131--1136.
Jeju Island, Korea. August 2007.
[Abstract]
[BibTeX]
[PDF]
The paper presents an approach to intelligent,
interactive people following for autonomous robots.
The approach combines robust methods for simultaneous
localization and mapping and for people tracking in
order to yield a socially and environmentally
sensitive people following behavior. Unlike current
purely reactive approaches ("nearest point
following") it enables the robot to follow
a human in a socially acceptable way, providing
verbal and non-verbal feedback to the user where
necessary. At the same time, the robot makes use of
information about the spatial and functional
organization of its environment, so that it can
anticipate likely actions performed by a human, and
adjust its motion accordingly. As a result, the
robot's behaviors become less reactive and more
intuitive when following people around an indoor
environment. The approach has been fully implemented
and tested.
@inproceedings{zender/etal:2007-roman,
author = {Hendrik Zender and Patric Jensfelt and Geert-Jan M. Kruijff},
title = {Human- and Situation-Aware People Following},
booktitle = {Proc. of the 16th IEEE International Symposium on Robot and Human
Interactive Communication (RO-MAN 2007)},
pages = {1131--1136},
address = {Jeju Island, Korea},
month = {August},
year = {2007}}
Hendrik Zender, Patric Jensfelt, Óscar Martínez Mozos,
Geert-Jan M. Kruijff, and Wolfram Burgard (2007).
An Integrated Robotic System for Spatial Understanding and Situated
Interaction in Indoor Environments
Proceedings of the Twenty-Second Conference on Artificial Intelligence
(AAAI-07), Special Track on Integrated Intelligence.
pp. 1584--1589.
Vancouver, BC, Canada. July 2007.
[Abstract]
[BibTeX]
[PDF]
[Poster PDF]
A major challenge in robotics and artificial intelligence
lies in creating robots that are to cooperate with people
in human-populated environments, e.g. for domestic assistance
or elderly care. Such robots need skills that allow
them to interact with the world and the humans living
and working therein. In this paper we investigate the
question of spatial understanding of human-made environments.
The functionalities of our system comprise
perception of the world, natural language, learning, and
reasoning. For this purpose we integrate state-of-the-art
components from different disciplines in AI, robotics
and cognitive systems into a mobile robot system. The
work focuses on the description of the principles we
used for the integration, including cross-modal integration,
ontology-based mediation, and multiple levels of
abstraction of perception. Finally, we present experiments
with the integrated "CoSy Explorer" system and
list some of the major lessons that were learned from its
design, implementation, and evaluation.
@inproceedings{zender/etal:2007-aaaiii,
author = {Hendrik Zender and Patric Jensfelt and \'{O}scar Mart\'{i}nez Mozos and
Geert-Jan M. Kruijff and Wolfram Burgard},
title = {An Integrated Robotic System for Spatial Understanding and
Situated Interaction in Indoor Environments},
booktitle = {Proc. of the Twenty-Second Conference on Artificial Intelligence (AAAI-07)},
pages = {1584--1589},
address = {Vancouver, British Columbia, Canada},
month = {July},
year = {2007}}
Óscar Martínez Mozos, Patric Jensfelt, Hendrik Zender,
Geert-Jan M. Kruijff, and Wolfram Burgard (2007a).
From Labels to Semantics: An Integrated System for Conceptual Spatial Representations
of Indoor Environments for Mobile Robots
Proceedings of the ICRA-07 Workshop on Semantic Information in Robotics (SIR).
pp. 33--40.
Rome, Italy. April 2007.
[Abstract]
[BibTeX]
[PDF]
We present an integrated approach for creating conceptual
representations of human-made environments using mobile robots. The concepts
represent spatial and functional properties of typical indoor environments. Our
model is composed of layers which represent maps at different levels of
abstraction. The complete system was integrated in a service robot which
is endowed with laser and vision sensors for place and object recognition.
It also incorporates a linguistic framework that actively supports the map
acquisition process and is used for situated dialogue.
In the experiments we show how the robot acquires the conceptual information
and how it is used for situational and functional awareness.
@inproceedings{mozos/etal:2007-icraws,
author = {\'{O}scar Mart\'{i}nez Mozos and Patric Jensfelt and Hendrik Zender
and Geert-Jan M. Kruijff and Wolfram Burgard},
title = {From Labels to Semantics: An Integrated System for Conceptual Spatial
Representations of Indoor Environments for Mobile Robots},
booktitle = {Proceedings of the ICRA-07 Workshop on Semantic Information in Robotics (SIR)},
pages = {33--40},
address = {Rome, Italy},
month = {April},
year = {2007}}
Hendrik Zender and Geert-Jan M. Kruijff (2007).
Multi-Layered Conceptual Spatial Mapping for Autonomous Mobile Robots
Papers from the AAAI Spring Symposium on
Control Mechanisms for Spatial Knowledge Processing in Cognitive / Intelligent Systems.
Menlo Park, CA, USA. March 2007.
[Abstract]
[BibTeX]
[PDF]
This paper presents an approach to spatial mapping for autonomous
mobile robots that are to operate among, and interact with, non-expert
human users. We argue that our approach of conceptual spatial
mapping helps bridge the gap between the representations needed for
low-level control of the robot, and the conceptual-topological
representations of space humans have. Our approach maintains spatial
knowledge on multiple interconnected layers. We show that a process
for map acquisition, human-augmented mapping, which combines
bottom-up and top-down influences from different modalities, will
yield a rich multi-layered spatial representation. This representation
enables the robot to perform complex actions in a human-populated
environment. We show that our approach can be used to establish a
notion of situational and functional awareness.
@inproceedings{zender/kruijff:2007-aaaisss,
author = {Hendrik Zender and Geert-Jan M. Kruijff},
title = {Multi-Layered Conceptual Spatial Mapping for Autonomous Mobile Robots},
booktitle = {Control Mechanisms for Spatial Knowledge Processing
in Cognitive / Intelligent Systems},
series = {Papers from the AAAI Spring Symposium},
editor = {Holger Schultheis and Thomas Barkowsky
and Benjamin Kuipers and Bernhard Hommel},
pages = {62--66},
year = {2007}
month = {March},
publisher = {AAAI Press},
volume = {Technical Report SS-07-01},
address = {Menlo Park, CA, USA}}
Geert-Jan M. Kruijff, Hendrik Zender, Patric Jensfelt, and Henrik I. Christensen (2007).
Situated Dialogue and Spatial Organization: What, Where... and Why?
International Journal of Advanced Robotic Systems (ARS), Special Issue on Human-Robot
Interaction.
Vol. 4, No. 1.
pp. 125--138. Ars International. March 2007.
[Abstract]
[BibTeX]
[PDF]
The paper presents an HRI architecture for human-augmented mapping, which has been implemented
and tested on an autonomous mobile robotic platform. Through interaction with a human, the
robot can augment its autonomously acquired metric map with qualitative information about locations
and objects in the environment. The system implements various interaction strategies observed
in independently performed Wizard-of-Oz studies. The paper discusses an ontology-based approach
to multi-layered conceptual spatial mapping that provides a common ground for human-robot dialogue.
This is achieved by combining acquired knowledge with innate conceptual commonsense knowledge in
order to infer new knowledge. The architecture bridges the gap between the rich semantic
representations of the meaning expressed by verbal utterances on the one hand and the robot's
internal sensor-based world representation on the other. It is thus possible to establish references
to spatial areas in a situated dialogue between a human and a robot about their environment.
The resulting conceptual descriptions represent qualitative knowledge about locations in the
environment that can serve as a basis for achieving a notion of situational awareness.
@article{kruijff/etal:2007-jars,
author = {Geert-Jan M. Kruijff and Hendrik Zender
and Patric Jensfelt and Henrik I. Christensen},
journal = {International Journal of Advanced Robotic Systems,
Special Issue on Human-Robot Interaction},
title = {Situated Dialogue and Spatial Organization: What, Where\ldots and Why?},
volume = {4},
number = {1},
pages = {125--138},
month = {March},
year = {2007}}
2006
Geert-Jan M. Kruijff, Hendrik Zender, Patric Jensfelt, and Henrik I. Christensen (2006b).
Situated dialogue and understanding spatial organization: Knowing what is where and what
you can do there.
Proceedings of the 15th IEEE International Symposium
on Robot and Human Interactive Communication (RO-MAN 2006).
pp. 328--333.
Hatfield, Hertfordshire, UK. September 2006.
[Abstract]
[BibTeX]
[PDF]
The paper presents an HRI architecture for human-augmented mapping.
Through interaction with a human, the robot can augment its
autonomously learnt metric map with qualitative information about
locations and objects in the environment. The system implements
various interaction strategies observed in independent Wizard-of-Oz
studies. The paper discusses an ontology-based approach to
representing and inferring 2.5-dimensional spatial organization we
adopt, and how knowledge of spatial organization can be acquired
autonomously or through spoken dialogue interaction.
@inproceedings{kruijff/etal:2006-roman,
author = {Geert-Jan M. Kruijff and Hendrik Zender
and Patric Jensfelt and Henrik I. Christensen},
title = {Situated Dialogue and Understanding Spatial Organization:
Knowing What Is Where and What You Can Do There},
booktitle = {Proceedings of the 15th IEEE International Symposium on
Robot and Human Interactive Communication (RO-MAN 2006)},
pages = {328--333},
address = {Hatfield, Hertfordshire, UK},
month = {September},
year = {2006}}
Hendrik Zender (2006).
Learning Spatial Organization Through Situated Dialogue.
Diplomarbeit (Diploma / MSc Thesis).
Saarland University, Dept. of Computational Linguistics,
Saarbrücken, Germany. August 2006.
[Abstract]
[BibTeX]
How shall a room be called? ...And why shall it be called that way?
How can a robot know what functions a room affords when it only knows its name?
And how can a robot know how to call a room when it has never been told the name of the room?
We claim that the most frequent general names people use to refer to rooms reflect how
people categorize rooms with respect to their functional properties. Knowing the general
name of a room such as kitchen as opposed to proper names like C +1.07 raises
expectations about what one is able to do there. By the same token, knowing what one
can do in a room means that one can refer to that room with a simple general name. The
hearer will then usually have similar hypotheses about specific properties of that room
without having seen it with his own eyes. Typically, a room's functional properties are
afforded by its geometric shape and spatial configuration, or by the objects that are located
therein. Hallways and corridors, for instance, are located in central places and by their
shapes afford easy passage to many other rooms. Kitchens, on the other hand, contain
objects needed for preparing a meal.
We have developed a cognitive architecture that allows a mobile robot to learn a multi-layered
conceptual-topological representation of the spatial organization of an indoor
environment, both autonomously and with human assistance. The topological representation
reflects the way humans segment space into distinct areas and how they are connected.
The conceptual representation contains verbally given assertions about locations
and objects that are found there. Our architecture contains facilities for reasoning about
categories of rooms based on (proto-)typical objects in such rooms.
Using this conceptual spatial representation, the robot is able to navigate its environment
and conduct a situated dialogue about its environment with a human user. We also
suggest how our method of conceptual spatial mapping and reasoning can be used as a
knowledge-base for higher-level planning mechanisms that enable the robot to execute
complex tasks in its environment.
The robot's behavior follows social patterns of human interaction. The conceptual-topological
representation that the robot acquires reflects the way people perceive of an
environment and allows for humanlike reasoning about the functional properties and general
names of rooms. Socially appropriate behavior of the robot and humanlike reasoning
capabilities facilitate human-robot interaction in a way that comforts users belonging to
the general public. Since users interact with the system through verbal communication,
non-expert users can intuitively control the robot's behavior and easily augment its internal
world knowledge. The complete cognitive system can thus be deployed for service
tasks in a human-populated indoor office environment.
@mastersthesis{zender:2006,
author = {Hendrik Zender},
title = {Learning Spatial Organization Through Situated Dialogue},
school = {Dept. of Computational Linguistics, Saarland University, Saarbrücken, Germany},
month = {August},
year = {2006}}
Geert-Jan M. Kruijff, Hendrik Zender, Patric Jensfelt, and Henrik I. Christensen (2006a).
Clarification dialogues in human-augmented mapping.
Proceedings of the 2006 ACM Conference on Human-Robot Interaction (HRI 2006).
pp. 282--288.
Salt Lake City, UT, USA. March 2006.
[Abstract]
[BibTeX]
[PDF]
An approach to dialogue based interaction for resolution of
ambiguities encountered as part of Human-Augmented Mapping (HAM) is
presented. The paper focuses on issues related to spatial organisation
and localisation. The dialogue pattern naturally arises as robots are
introduced to novel environments. The paper discusses an approach
based on the notion of Questions under Discussion (QUD). The presented
approach has been implemented on a mobile platform that has dialogue
capabilities and methods for metric SLAM. Experimental results from a
pilot study clearly demonstrate that the system can resolve
problematic situations.
@inproceedings{kruijff/etal:2006-hri,
author = {Geert-Jan M. Kruijff and Hendrik Zender
and Patric Jensfelt and Henrik I. Christensen},
title = {Clarification Dialogues in Human-Augmented Mapping},
booktitle = {Proceedings of the 2006 ACM Conference on Human-Robot Interaction (HRI 2006)},
pages = {282--288},
address = {Salt Lake City, UT, USA},
month = {March},
year = {2006}}
Projects
NIFTi: Natural Human-Robot Cooperation in Dynamic Environments
CogX: Cognitive Systems that Self-Understand and Self-Extend
COSY: Cognitive Systems for Cognitive Assistants
Affiliations
DFKI
The DFKI Language Technolgy Lab
Talking Robots @ the DFKI LT Lab
Events and Calls
Call for papers: International Journal of Social Robotics (SORO),
Special Issue on Expectations, Intentions, and Actions
ICAIR workshop at ICRA 2010: Interactive Communication for Autonomous Intelligent Robots
SI3R workshop at ICRA 2008: Social Interaction with Intelligent Indoor Robots
|