Advances in Plan-Based Control of Robotic Agents

Abstract

PrefaceIn recent years, autonomous robots, including Xavier, Martha [1], Rhino [2,3], Minerva, and Remote Agent, have shown impressive performance in long-term demonstrations. In NASA's Deep Space program, for example, an autonomous spacecraft controller, called the Remote Agent [5], has autonomously performed a scientific experiment in space. At Carnegie Mellon University, Xavier [6], another autonomous mobile robot, navigated through an office environment for more than a year, allowing people to issue navigation commands and monitor their execution via the Internet. In 1998, Minerva [7] acted for 13 days as a museum tourguide in the Smithsonian Museum, and led several thousand people through an exhibition.These autonomous robots have in common that they rely on plan-based control in order to achieve better problem-solving competence. In the plan-based approach, robots generate control actions by maintaining and executing a plan that is effective and has a high expected utility with respect to the robots' current goals and beliefs. Plans are robot control programs that a robot can not only execute but also reason about and manipulate [4]. Thus, a plan-based controller is able to manage and adapt the robot's intended course of action -the plan -while executing it and can thereby better achieve complex and changing tasks. The plans used for autonomous robot control are often reactive plans, that is, they specify how the robots are to respond in terms of low-level control actions to continually arriving sensory data in order to accomplish their objectives. The use of plans enables these robots to flexibly interleave complex and interacting tasks, exploit opportunities, quickly plan their courses of action, and, if necessary, revise their intended activities.The emergence of complete plan-based robot control systems, on the one hand, and the lack of integrated computational models of plan-based control, on the other hand, motivated us to organize a Dagstuhl seminar "Plan-Based Control of Robotic Agents" 1 at Schloss Dagstuhl (21-26 October 2001). The purpose of this seminar was to bring together researchers from different fields in order to promote information exchange and interaction between research groups working on various aspects of plan-based autonomous robot control.The objective was to identify computational principles that enable autonomous robots to accomplish complex, diverse, and dynamically changing tasks in challenging environments. These principles include plan-based high-level control, probabilistic reasoning, plan transformation, and context and resourceadaptive reasoning. The development of comprehensive and integrated computational models of plan-based control requires us to consider different aspects of plan-based control -plan representation, reasoning, execution, and learningtogether and not in isolation. Such integrated approaches enable us to exploit synergies between the different aspects and thereby come up with simpler and more powerful computational models.1 For more information on the Se...