Gibson’s theory of affordance, in its adherence to bottom-up direct perception, is antithetical to the top-down inferential models often proposed by modern robotics research purporting to tackle it. Such research assumes internal representation to be sacrosanct, but given current developments, to what extent can this assumption now be reexamined? The recently proposed sensorimotor contingency theory furthers the theoretical argument that internal representation is unnecessary, and its proof-of-concept application in robotics as well as the subsequent explosion in deep learning methodology sheds new light on the possibility of equipping robots with the capacity for directly perceiving their environments by exploiting correlated changes in their sensory inputs triggered by executing specific motor programs. This reexamination of direct perception is only one of several issues warranting scrutiny in current robotic affordance research. The aim of this workshop is therefore twofold.
Firstly, we will provide an overview of the state-of-the-art in affordance research and dissect open research challenges yielded thereof.
Secondly, we will encourage our speakers to debate whether computational models of affordance can potentially be advanced by adopting approaches that are more congruent with Gibson’s original conception of direct perception.
This workshop proposal is a sequel to the 1st edition of the International Workshop on Computational Models of Affordance in Robotics at RSS 2018. The rich and interdisciplinary discussions that took place there call for a second edition. Additionally, as the survey below shows , affordances are a topic of high interest in robotics, readily showing that such an interdisciplinary workshop is of high relevance to advance affordance research in robotics.
 Philipp Zech, Simon Haller, Safoura Rezapour Lakani, Barry Ridge, Emre Ugur, Justus Piater, Computational models of affordance in robotics: a taxonomy and systematic classification. Adaptive Behavior, 25 (5), pp. 235–271, 2017. SAGE.
- Affordance learning
- Multimodal affordance learning
- Affordance perception and vision for affordances
- Perceptual learning and development
- Babbling and exploration
- Language and affordances
- Learning from observation and mirroring
- Self-organization of knowledge
- Deep learning of affordances
- Bayesian learning of affordances
- Concept learning
- Symbol emergence
- Symbol grounding
- Sensorimotor contingency theory
- Behavior affording behavior
- Actions and functions in object perception
- Brain-body-environment systems
- Agent-environment systems
- Selective attention
- Self-supervised learning
- Sensing physical properties
- Ecologically intuitive physics
Call for Contributions
Participants are invited to submit contributions related to the aforementioned topics in one of the following categories:
- Extended abstract (maximum 2 pages in length)
- Full paper (maximum 8 pages in length)
Submissions must be in PDF following the ICRA style available from
and uploaded via the Microsoft CMT conference management system at
- Submission Deadline: 01.05.2019
- Notification of Acceptance: 07.05.2019
- Camera ready submission: 22.05.2019
- Workshop: 23 or 24 May 2019
Submission are expected to follow the official ICRA style available at https://www.ieee.org/conferences/publishing/templates.html. Contributions are to be submitted via Microsoft CMT at https://cmt3.research.microsoft.com/IWCMAR2019.
All submissions will be peer-reviewed. Accepted papers will be presented during the workshop in a poster session. Outstanding papers will be presented as oral spotlight talks and invited to submit an extended version to a special issue of Frontiers in Neurorobotics on “Computational Models of Affordance for Robotics”, a journal published by Frontiers. The review process for the journal is independent from the review for this workshop.
A Frontiers in NeuroRobotics special issue is being organized in tandem with the workshop. While workshop contributors will be invited to submit extended versions of their workshop papers, general submissions will also be welcome.
Stay tuned for further announcements.
The accepted papers are listed as follows:
- To be populated after camera ready submission deadline.
- Yiannis Aloimonos (Perception and Robotics Group, University of Maryland)
- Tamim Asfour (High Performance Humanoid Technologies, Karlsruhe Institute of Technology)
- Paul Cisek (Department of Neuroscience, University of Montréal)
- Claire Michaels (Centre for the Ecological Study of Perception and Action, University of Connecticut)
The final schedule will be publish upon finalization of the list of speakers.
Stay tuned for further announcements,
|11:30-12:00||Time buffer for discussions after invited talks|
Please check out https://www.icra2019.org/montreal-travel/conference-venue as well as https://www.icra2019.org/program/program-overview for detailed information on the workshop’s location.
- Philipp Zech is a postdoctoral researcher at the University of Innsbruck. He received his Ph.D. degree in Computer Science from the University of Innsbruck in 2014. He is interested in developmental and cognitive robotics, affordance learning and intelligent and adaptive manipulation. He has already published more than 30 papers in international journals and conferences, two of which have received best-paper awards. He currently serves as an associate editor for Adaptive Behavior.
- Erwan Renaudo is a postdoctoral researcher at the University of Innsbruck. He completed his PhD degree in 2016 at Pierre and Marie Curie University where he worked on bio-inspired robotic architectures with ensemble reinforcement learning. His research interests focus on learning methods for autonomous robots. He is particularly interested in autonomous behavior generation, from action learning to coordination of habitual and goal-directed behaviors.
- Peter Kaiser is a postdoctoral researcher at the High Performance Humanoid Technologies Lab of the Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology (KIT). He received his Ph.D. from KIT in 2017. His major research interests include the perception of action possibilities in unknown environments, as well as the planning and execution of whole-body actions that combine locomotion and manipulation in the context of humanoid robotics.
- Raja Chatila, IEEE Fellow, is Professor of Artificial Intelligence, Robotics and Ethics at Pierre and Marie Curie University in Paris, France. He is director of the SMART Laboratory of Excellence on Human-Machine Interactions and former director of the Institute of Intelligent Systems and Robotics. He contributed in several areas of Artificial Intelligence and autonomous and interactive Robotics along his career. His research interests currently focus on human-robot interaction, machine learning and ethics.