Barták, Roman


Special Track on Autonomous Robots and Agents

AAAI Conferences

Robotics and artificial intelligence are closely related areas though their research interests and topics diverted in past. Recently, the progress in both areas brings robotics and artificial intelligence together again and higher-level deliberative functions such as action planning are being integrated into usually reactive robotics systems to increase their autonomy as well as to simplify their control. This special track addresses research results on the border between robotics (and general intelligent agents) and AI techniques with the aim of bridging the enlarging gap between the areas.


Reports of the Workshops of the Thirty-First AAAI Conference on Artificial Intelligence

AI Magazine

Reports of the Workshops of the Thirty-First AAAI Conference on Artificial Intelligence


Guiding Planning Engines by Transition-Based Domain Control Knowledge

AAAI Conferences

Domain-independent planning requires only to specify planning problems in a standard language (e.g. PDDL) in order to utilise planning in some application. Despite a huge advancement in domain-independent planning, some relatively-easy problems are still challenging for existing planning engines. Such an issue can be mitigated by specifying Domain Control Knowledge (DCK) that can provide better guidance for planning engines. In this paper, we introduce transition-based DCK, inspired by Finite State Automata, that is efficient as demonstrated empirically, planner-independent (can be encoded within planning problems) and easy to specify.


Special Track on Intelligent Autonomous Systems

AAAI Conferences

The aim of the special track is to bring researchers from related but still separated areas of robotics and artificial intelligence together to study how high-level AI techniques such as action planning and knowledge representation may help in increasing capabilities of robotic systems.