A robot companion's system needs to be endowed with an internal representation of ‘the world' in order to reason, plan and to interact with people. We focus on representations of the world around it, needed for navigation, and representations of objects, needed for interaction. The robot has to estimate ‘where' it is (or where the object is) and ‘what' it is (for example ‘the kitchen' for space, or ‘the bottle' for objects).

Partners involved

RA leader : UvA

partners involved : UvA, LAAS, EPFL, KTH, IPA, UniKarl, UniBi

RA objectives

RA5 addresses the understanding of how an embodied system can come to a conceptualisation of sensory-motor data, generate plans and actions to navigate and manipulate in typical home settings. The concept formation is considered in a broad sense, i.e. the ability to interpret situations, i.e. states of the environment and relationships between components of the environment that are static or evolving over time. The robot can observe these states or be part of the evolving action itself.

The robot will use different sensing modalities, and can also act in order to improve its understanding of the situation or to disambiguate its interpretation.

The following questions will be studied in RA5 :
the representation of space
the representation of situations
the representation and recognition of objects
dynamics and actions

Work conducted in RA5 is related to all three Key Experiments :

Work on models of spaces is directly relevant to Key Experiment 1. The robot must indeed be able to categorize space and reason about it and plan at an abstract level. At the same time the system must be able to navigate accurately through doorways or corridors, which requires a lower-level, sensory representation.

Work on models of objects is directly related to all three Key Experiments : the Robot Home Tour (using objects as landmarks), the Curious Robot (learning new objects), and the Task and Skill learning (learning object manipulation).

Related project publications

Below are only listed some of the RA5-related publications, please see the Publications page for more.

Zivkovic, Z, Bakker, B., and Kröse, B. , Hierarchical Map Building Using Visual Landmarks and Geometric Constraints , Submitted to IEEE/RSJ International Conference on Intelligent Robots and Systems, Canada, 2005

Nicolas Do Huu, Williams Paquier , Raja Chatila, Combining structural description and image-based representation for image, object, and scene recognition, IJCAI 2005

Elin A. Topp and Henrik I. Christensen, Tracking for Following and Passing Persons, Submitted to IROS2005

Adriana Tapus, Shrihari Vasudevan and Roland Siegwart, Towards a Multilevel Cognitive Probabilistic Representation of Space, In the proceedings of the International Conference on Human Vision and Electronic Imaging X, part of the IS&T/SPIE Symposium on Electronic Imaging 2005, 16-20 January 2005, CA, USA (HVEI 2005)