The goal of execution monitoring is to determine whether a system or person is fonowmg a plan appropriately. Monitoring information may be uncertain, and the plan being monitored may have complex temporal constraints. We develop a new framework for reasoning under uncertainty with quantitative temporal constraints - Quantitative Temporal Dynamic Bayesian Networks - and we discuss its application to plan-execution monitoring. QTDBNs extend the major previous approaches to temporal reasoning under uncertainty: Time Nets (Kanazawa 1991), Dynamic Bayesian Networks and Dynamic Object Oriented Bayesian Networks (Friedman, Koller, £" Pfeffer 1998). We argue that Time Nets can model quantitative temporal relationships but cannot easily model the changing values of fluents, while DBNs and DOOBNs naturally model fluents, but not quantitative temporal relationships. Both capabilities are required for execution monitoring, and are supported by QTDBNs. Introduction The goal of execution monitoring is to determine whether a system or person is following a plan appropriately or is heading toward a failure state. Most execution monitoring systems build an internal model of the domain and use sensor inputs to update the model. Because sensors are error-prone, the execution monitoring process must be able to reason under uncertainty. Bayesian belief networks that support plan execution monitoring under uncertainty can be generated directly from the plans being monitored (Huber, Durfee, & Wellman 1994).
The aging of the world's population poses a challenge and an opportunity for the design of intelligent technology. This paper focuses on one type of assistive technology, cognitive orthotics, which can help people adapt to cognitive declines and continue satisfactory performance of routine activities, thereby potentially enabling them to remain in their own homes longer. Existing cognitive orthotics mainly provide alarms for prescribed activities at fixed times that are specified in advance. In contrast, we describe Autominder, a system we have designed that uses AI planning and plan management technology to carefully model an individual's daily plans, attend to and reason about the execution of those plans, and make flexible and adaptive decisions about when it is most appropriate to issue reminders. The paper concentrates on one of Autominder's three main components, the Plan Manager; other papers in this volume describe its other components (Colbry, Peintner, & Pollack 2002; McCarthy & Pollack 2002).
A current popular approach to representing time in Bayesian belief networks is through Dynamic Bayesian Networks (DBNs) (Dean & Kanazawa 1989). DBNs connect sequences of entire Bayes networks, each representing a situation at a snapshot in time. We present an alternative method for incorporating time into Bayesian belief networks that utilizes abstractions of temporal representation. This method maintains the principled Bayesian approach to reasoning under uncertainly, providing explicit representation of sequence and potentially complex temporal relationships, while also decreasing overall network complexity compared to DBNs.
The Nursebot project is a multi-disciplinary, multi-university effort aimed at developing mobile robotic assistants for the elderly. In this paper, we describe one such robot, Pearl. Pearl has two primary functions: (i) reminding people about routine activities such as eating, drinking, taking medicine, and using the bathroom, and (ii) guiding them through their environments. We provide a brief overview of the hardware platform, and we sketch the major software systems that enable Pearl to perform its two main functions. A prototype version of Pearl has been completely built, with all software implemented, and preliminary testing has been done at the Longwood Retirement Community in Oakmont, PA.
This paperconsiders the problem of representing complex systems that evolve stochastically over time. Dynamic Bayesian networks provide a compact representation for stochastic processes. Unfortunately, they are often unwieldy since they cannot explicitly model the complex organizational structure of many real life systems: the fact that processes are typically composed of several interacting subprocesses, each of which can, in turn, be further decomposed. We propose a hierarchically structured representation language which extends both dynamic Bayesian networks and the object-oriented Bayesian network framework of , and show that our language allows us to describe such systems in a natural and modular way. Our language supports a natural representation for certain system characteristics that are hard to capture using more traditional frameworks. For example, it allows us to represent systems where some processes evolve at a different rate than others, or systems where the processes interact only intermittently. We provide a simple inference mechanism for our representation via translation to Bayesian networks, and suggest ways in which the inference algorithm can exploit the additional structure encoded in our representation.