High-level control for Autonomous Systems (e.g. robots) is concerned with selecting the next action the system should perform. In particular this means that the system must be endowed with algorithms or schemes to take the next step towards its mission goal. The known paradigms for this action selection problem are learning, deliberation, reactive control schemes or combinations of these schemes, i.e. hybrid approaches.
Learning has been applied successfully to many robotics tasks. Most of the work is related to learning certain basic behaviors or skills. Examples where the high-level control strategy of robots (or agents) were successfully learned are rare. The deliberative approach for decision making of autonomous systems was successfully treated in research on Artificial Intelligence, following a top-down approach, which has severe limitations in real applications. In the reactive control paradigm the idea is that, with a combination of purely reactive action selection schemes, intelligent and goal-directed behaviors emerge, which can be seen as a bottom-up approach.
These different paradigms have been known for over two decades, and in fact, in today's applications, often combinations of learning, deliberation and reactive control are used. Usually these combinations are used in an ad-hoc or even unconscious fashion. Although there is a number of proposed architectures and huge body of literature, the issue of combining learning, reactive and deliberative control never has been intensively investigated.
With this workshop we wish to bring together researchers from different areas who concentrate on combinations of learning, planning, and/or reactive schemes for decision making and the control of autonomous systems. The workshop is open to all members of the AI and Robotics community. We would specifically like to encourage students to participate.
Topics
The questions to be addressed in this workshop are:

* How can learning, deliberation and/or reactive control be combined in a beneficial way?
* What are common representations for learning, deliberation, and/or reactive control such that the methods can benefit from each other?
* What are the challenging domains demanding for hybrid control?
* What are its successful applications?

We solicit work from these areas:

* Decision Making
* Modeling of Domains and Capabilities
* Agent Learning
* Cognitive Robotics
* Emergent Control
* Behavior-based Robotics
* Developmental and Epigenetic Robotics
* Learning Models of Robot Behaviors
* Monitoring
* Architectures and Architectural Patterns
* Applications of Hybrid Control

Location and Dates
The first HYCAS workshop will be held in Pasadena, California, USA, in July 2009 in conjunction with the 21st International Joint Conference on Artificial Intelligence (IJCAI-09).

Call for Papers
The call for papers can be downloaded as a PDF file here.
Workshop Objectives
High-level control for Autonomous Systems (e.g. robots) is concerned with selecting the next action the system should perform. Known paradigms for this action selection problem are learning, deliberation, reactive control schemes or combinations of these, i.e. hybrid approaches.
Most of the research on robot learning is related to learning certain basic behaviours or skills. Examples where the high-level control strategy of robots (or other agents) was successfully learned are rare. The deliberative approach for decision making for autonomous systems was successfully treated in Artificial Intelligence research, following a top-down approach, which has severe limitations in real applications. In the reactive control paradigm the idea is that with a combination of purely reactive action selection schemes, intelligent and goal-directed behaviours emerge, which can be seen as a bottom-up approach.
These different paradigms have been known for over two decades, and in today's applications often combinations of learning, deliberation, and reactive control are used. Usually these combinations are used in an ad-hoc or even unconscious fashion. Although there is a number of proposed architectures and huge body of literature, the issue of combining learning, reactive and deliberative control never has been intensively investigated.
With this workshop we wish to bring together researchers from different areas who concentrate on combinations of learning, planning, and/or reactive schemes for decision making and the control of autonomous systems. The workshop is open to all members of the AI and Robotics community. We would specifically like to encourage students to participate.
Relevant Topics
Papers are invited on all aspects of hybrid methods for the control of autonomous systems, including, but not limited to:

* Decision Making
* Modelling of Domains, Capabilities/Affordances and Robot Behaviours
* Agent Learning
* Cognitive Robotics
* Behaviour-based Robotics and Emergent Control
* Developmental and Epigenetic Robotics
* Monitoring
* Architectures and Architectural Patterns
* Applications of Hybrid Control

Authors of selected articles will be invited to submit an extended version of their workshop paper to a special issue of an international journal on robotics and automation.
Submission Dates

* March 6 2009: Paper submission deadline
* April 17 2009: Notification of paper acceptance
* May 8 2009: Camera ready paper submission
* May 15 2009: Early registration deadline
* July 11, 12 or 13 2009 (tba): Workshop takes place

The initial paper submission deadline is on March 6 2009 at 23:59 UTC (GMT).