| 1. |
- Pronobis, Andrzej, et al.
(författare)
-
Semantic modelling of space
- 2010. - 8
-
Ingår i: Cognitive Systems Monographs. - Berlin, Heidelberg : Springer Berlin/Heidelberg. - 9783642116940 ; , s. 165-221
-
Bokkapitel (refereegranskat)abstract
- A cornerstone for robotic assistants is their understanding of the space they are to be operating in: an environment built by people for people to live and work in. The research questions we are interested in in this chapter concern spatial understanding, and its connection to acting and interacting in indoor environments. Comparing the way robots typically perceive and represent the world with findings from cognitive psychology about how humans do it, it is evident that there is a large discrepancy. If robots are to understand humans and vice versa, robots need to make use of the same concepts to refer to things and phenomena as a person would do. Bridging the gap between human and robot spatial representations is thus of paramount importance. A spatial knowledge representation for robotic assistants must address the issues of human-robot communication. However, it must also provide a basis for spatial reasoning and efficient planning. Finally, it must ensure safe and reliable navigation control. Only then can robots be deployed in semi-structured environments, such as offices, where they have to interact with humans in everyday situations. In order to meet the aforementioned requirements, i.e. robust robot control and human-like conceptualization, in CoSy, we adopted a spatial representation that contains maps at different levels of abstraction. This stepwise abstraction from raw sensory input not only produces maps that are suitable for reliable robot navigation, but also yields a level of representation that is similar to a human conceptualization of spatial organization. Furthermore, this model provides a richer semantic view of an environment that permits the robot to do spatial categorization rather than only instantiation. This approach is at the heart of the Explorer demonstrator, which is a mobile robot capable of creating a conceptual spatial map of an indoor environment. In the present chapter, we describe how we use multi-modal sensory input provided by a laser range finder and a camera in order to build more and more abstract spatial representations.
|
|
| 2. |
- Sjöö, Kristoffer, et al.
(författare)
-
The explorer system
- 2010. - 8
-
Ingår i: Cognitive Systems Monographs. - Berlin, Heidelberg : Springer Berlin/Heidelberg. - 9783642116940 ; , s. 395-421
-
Bokkapitel (refereegranskat)abstract
- In the Explorer scenario we deal with the problems of modeling space, acting in this space and reasoning about it. Spatial models are built using input from sensors such as laser scanners and cameras but equally importantly also based on human input. It is this combination that enables the creation of a spatial model that can support low level tasks such as navigation, as well as interaction. Even combined, the inputs only provide a partial description of the world. By combining this knowledge with a reasoning system and a common sense ontology, further information can be inferred to make the description of the world more complete. Unlike the PlayMate system, all the information that is needed to build the spatial models are not available to it sensors at all times. The Explorer need to move around, i.e. explorer space, to gather information and integrate this into the spatial models. Two main modes for this exploration of space have been investigated within the Explorer scenario. In the first mode the robot explores space together with a user in a home tour fashion. That is, the user shows the robot around their shared environment. This is what we call the Human Augmented Mapping paradigm. The second mode is fully autonomous exploration where the robot moves with the purpose of covering space. In practice the two modes would both be used interchangeably to get the best trade-off between autonomy, shared representation and speed. The focus in the Explorer is not on performing a particular task to perfection, but rather acting within a flexible framework that alleviates the need for scripting and hardwiring. We want to investigate two problems within this context: what information must be exchanged by different parts of the system to make this possible, and how the current state of the world should be represented during such exchanges. One particular interaction which encompasses a lot of the aforementioned issues is giving the robot the ability to talk about space. This interaction raises questions such as: how can we design models that allow the robot and human to talk about where things are, and how do we link the dialogue and the mapping systems?
|
|
| 3. |
- Wyatt, Jeremy L., et al.
(författare)
-
Self-Understanding and Self-Extension : A Systems and Representational Approach
- 2010
-
Ingår i: IEEE T AUTON MENT DE. - 1943-0604. ; 2:4, s. 282-303
-
Tidskriftsartikel (refereegranskat)abstract
- 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 explicit representation of and reasoning about what a system does and does not know, and how that knowledge changes under action. We present an architecture and a set of representations used in two robot systems that exhibit a limited degree of autonomous mental development, which we term self-extension. The contributions include: representations of gaps and uncertainty for specific kinds of knowledge, and a goal management and planning system for setting and achieving learning goals.
|
|
