Planning under uncertainty is a central problem in the study of automated sequential decision making, and has been addressed by researchers in many different fields, including AI planning, decision analysis, operations research, control theory and economics. While the assumptions and perspectives adopted in these areas often differ in substantial ways, many planning problems of interest to researchers in these fields can be modeled as Markov decision processes (MDPs) and analyzed using the techniques of decision theory. This paper presents an overview and synthesis of MDP-related methods, showing how they provide a unifying framework for modeling many classes of planning problems studied in AI. It also describes structural properties of MDPs that, when exhibited by particular classes of problems, can be exploited in the construction of optimal or approximately optimal policies or plans. Planning problems commonly possess structure in the reward and value functions used to de...

Introduction Within the ATAL community, the belief-desire-intention (BDI) model has come to be possibly the best known and best studied model of practical reasoning agents. There are several reasons for its success, but perhaps the most compelling are that the BDI model combines a respectable philosophical model of human practical reasoning, (originally developed by Michael Bratman [1]), a number of implementations (in the IRMA architecture [2] and the various PRS-like systems currently available [7]), several successful applications (including the now-famous fault diagnosis system for the space shuttle, as well as factory process control systems and business process management [8]), and finally, an elegant abstract logical semantics, which have been taken up and elaborated upon widely within the agent research community [14, 16]. However, it could be argued that the BDI model is now becoming somewhat dated: the principles of the architecture were established in the mid-1980s,

This paper describes Autominder, a cognitive orthotic system intended to help older adults adapt to cognitive decline and continue the satisfactory performance of routine activities, thereby potentially enabling them to remain in their own homes longer. Autominder achieves this goal by providing adaptive, personalized reminders of (basic, instrumental, and extended) activities of daily living. Cognitive orthotic systems on the market today mainly provide alarms for prescribed activities at fixed times that are specified in advance. In contrast, Autominder uses a range of AI techniques to model an individual's daily plans, observe and reason about the execution of those plans, and make decisions about whether and when it is most appropriate to issue reminders. Autominder is currently deployed on a mobile robot, and is being developed as part of the Initiative on Personal Robotic Assistants for the Elderly (the Nursebot project)

Abstract not found

Abstract not found

Case-base maintenance is gaining increasing recognition in research and the practical applications of case-based reasoning (CBR). This intense interest is highlighted by Smyth and Keane's research on case deletion policies. In their work, Smyth and Keane advocated a case deletion policy, whereby the cases in a case base are classified and deleted based on their coverage potential and adaptation power. The algorithm was empirically shown to improve the competence of a CBR system and outperform a number of previous deletion-based strategies. In this paper, we present a different case-base maintenance policy that is based on case addition rather than deletion. The advantage of our algorithm is that we can place a lower bound on the competence of the resulting case base; we demonstrate that the coverage of the computed case base cannot be worse than the optimal case base in coverage by a fixed lower bound, and the coverage is often much closer to optimum. We also show that the Smyth and Ke...

: For many years, research in AI plan generation was governed by a number of strong, simplifying assumptions: that the planning agent is omniscient, that its actions are deterministic and instantaneous, that its goals are fixed and categorical, and that its environment is static. More recently, researchers have developed expanded planning algorithms that are not predicated on such assumptions. But changing the way in which plans are formed is only part of what is required when the classical assumptions are abandoned. The demands of dynamic, uncertain environments mean that in addition to being able to form plans---even probabilistic, uncertain plans---agents must be able to effectively manage their plans. In this paper, which is based on a talk given at the 1998 AAAI Fall Symposium on Distributed, Continual Planning, we first identify reasoning tasks that are involved in plan management, including commitment management, environment monitoring, alternative assessment, plan elaboration, ...

Abstract not found

Abstract. Flexible support for crisis management can definitely be improved by making use of advanced planning capabilities. However, the complexity of the underlying domain often causes intractable efforts in modeling the domain as well as a huge search space to be explored by the system. A way to overcome these problems is to impose a structure not only according to tasks but also according to relationships between and properties of the objects involved, thereby using so-called decomposition axioms. We outline the prototype of a system that is capable of tackling planning for complex application domains. It is based on a well-founded combination of action and state abstractions. The paper presents the basic techniques and provides a formal semantic foundation of the approach. It introduces the planning system and illustrates its underlying principles by examples taken from the crisis management domain used in our ongoing project. 1

We present a robot control system for known structured environments that integrates robust reactive control with reasoning-based execution monitoring. It provides a robot with a powerful method for dealing with situations that were caused by the interaction with humans or that are due to unexpected changes in the operating environment. On the reactive level, the robot is controlled using a hierarchy of low-level behaviours. On the high level, a logical representation of the world enables the robot to plan action sequences and to reason about the state of the world. If the execution of an action does not have the expected effect, high-level reasoning allows the robot to infer possible explanations and, if necessary, to recover from the failure situation. For the robot to act optimally, the discrepancies between the internal world model and the real world have to be detected and corrected. The proposed system obtains new information about the world by executing sensing actions (active perception) and by sensory interpretation during the robot's operation. It also takes into account temporal information about changes in the environment. All updates of the world model are performed in a way that the changes are consistent with an underlying action theory. Having implemented the proposed system on a common mobile robot platform, we demonstrate the value of intelligent execution monitoring by means of two realistic office delivery scenarios.