Automated Action Planning for Autonomous Mobile Robots
Papers from the 2011 AAAI Workshop
Sanem Sariel-Talay, Stephen F. Smith, Nilufer Onder, Workshop Cochairs
The purpose of this workshop is to bring researchers from the automated planning and mobile robotics communities together to investigate the research issues on the use of automated high-level action planning techniques for mobile robots. Recently, there have been significant advances in both fields. Path or trajectory planning has dealt with realistic issues such as localization, mapping and efficient navigation techniques for mobile robots. Automated planning research has focused on devising efficient action planners that scale up to large planning problems. International Planning Competitions (IPC) have emerged as standard platforms to test and validate the success of novel planners and to determine the limits imposed by enhanced domain representations with realistic constraints.
However, path or trajectory planning algorithms operate at a low level, thus they are not able to deal with complex missions involving interrelated actions. Similarly, action planning algorithms operate at a high level and thus are not able to deal with the hardware and physical environment limitations. In addition to simple navigation tasks, high-level automated planning techniques are essential for robots to perform complex missions involving interrelated actions. Considerable progress has been made in both fields and it is the right time for fostering interaction.
Robots as embodied agents provide convenient tools to test and validate high-level planners on real planning problems. This workshop aims to foster the exchange of ideas and to promote research on automated planning representations, models and algorithms for mobile robots to achieve complex planning tasks. The emphasis will be placed on the formal aspects of action planning for mobile robots. The use of the latest promising action planners on mobile robots, their applicability and action/domain representation issues will be analyzed.