Narrow Results

Active vision systems can be considered as systems that integrate visual sensing and action. Sensing includes detection of actions/events and results also in specific actions/manipulations.

This paper mainly addresses the basic issues in the design of a head-eye system for the study of active-purposive vision. The design complexity of such a head is defined by the activeness of the visual system. Although we have not had the motivation to exactly reproduce the biological solutions in a robot, we claim that the designer should carefully consider the solutions offered by evolution.

The flexibility of the behavioral pattern of the system is constrained by the mechanical structure and the computational architecture used in the control system of the head. The purpose of the paper is to describe the mechanical structure as well as the computational architecture of the KTH-head from this perspective.

A use case is a specification of interactions involving a system and external actors of that system. The intuitive, user centered nature of textual use cases is one of the reasons for the success of the use case approach. A certain level of formalization is however needed to automate use case based system development, including tasks such as design synthesis, verification and validation. In this paper, a mapping from textual use cases to a formal model (Petri nets) is proposed. Use cases are described in a restricted-form of natural language. The abstract syntax of the language is formally defined using a tuple structure. The mapping from use cases to Petri nets considers use cases sequencing constraints defined at the syntactic-level, and provides a definition of execution semantics to use cases.

Tasks that change the physical state of a robot and its environment take a considerable amount of time to execute. However, many robot applications spend the execution time waiting, although the following tasks might require time to prepare. This paper proposes to amend robot tasks with a semantic description of their expected outcomes, which allows planning and preparing successive tasks based on this information. The suggested approach allows sequential and parallel compositions of tasks, as well as reactive behavior modeled as state machines. The paper describes the means of modeling and executing these tasks, details different possibilities of planning in state-machine tasks and evaluates the benefits achievable using the approach on two example scenarios.

Tasks that change the physical state of a robot and its environment take a considerable amount of time to execute. However, many robot applications spend the execution time waiting, although the following tasks might require time to prepare. This paper proposes to amend robot tasks with a semantic description of their expected outcomes, which allows planning and preparing successive tasks based on this information. The suggested approach allows sequential and parallel compositions of tasks, as well as reactive behavior modeled as state machines. The paper describes the means of modeling and executing these tasks, details different possibilities of planning in state-machine tasks and evaluates the benefits achievable using the approach on two example scenarios.

Active vision systems can be considered as systems that integrate visual sensing and action. Sensing includes detection of actions/events and results also in specific actions/manipulations.

This paper mainly addresses the basic issues in the design of a head-eye system for the study of active-purposive vision. The design complexity of such a head is defined by the activeness of the visual system. Although we have not had the motivation to exactly reproduce the biological solutions in a robot, we claim that the designer should carefully consider the solutions offered by evolution.

The flexibility of the behavioral pattern of the system is constrained by the mechanical structure and the computational architecture used in the control system of the head. The purpose of the paper is to describe the mechanical structure as well as the computational architecture of the KTH-head from this perspective.

The brittle nature and the computational complexity of the state of the art “classical” planning systems such as MOLGEN and SIPE when applied to ‘real-world’ problem domains such as robotics has become evident. Uncertainty about the effects of actions and the state of the environment, in addition to dynamic effects caused by other active agents made these approaches wholly insufficient. Reactive systems, an approach that started to remedy this, generates robust and responsive behavior, but does not support a priori deliberation and globally optimal behavior.

In this chapter, we introduce incremental adaptation as a method to improve reactive behavior. This methodology aims to get the best of both worlds, the fast response of the reactive systems and the deliberative capability of planning systems. Unlike in the latter, a plan does not have to be generated all at once. Rather, the reactive control strategy can be incrementally adapted to better suit the current environment and the possibly changing objectives. We discuss the advantages of this methodology and present a survey of systems using incremental adaptation.