O-Plan is an AI planner based on previous experience with the Nonlin planner and its derivatives. Nonlin and other similar planning systems had limited control architectures and were only partially successful at limiting their search spaces. O-Plan is a design and implementation of a more flexible system aimed at supporting planning research and development, opening up new planning methods and supporting strong search control heuristics. O-Plan takes an engineering approach to the construction of an efficient domain independent planning system which includes a mixture of AI and numerical techniques from Operations Research. The main contributions of the work are centred around the control of search within the OPlan planning framework, and this paper outlines the search control heuristics employed within the planner. These involve the use of condition typing, time and resource constraints and domain constraints to allow knowledge about an application domain to be used to prune the searc...

A Dissertation Presented by TUOMAS W. SANDHOLM

This paper describes the O-Plan2 agent oriented architecture and describes the communication which takes place between planning and execution monitoring agents built upon the architecture. Separate modules of such a system are identified along with internal and external interface specifications that form a part of the design. Time constraints, resource usage, object selection and condition/effect causal constraints are handled as an integral part of the overall system structure by treating specialised constraint management as supporting the core decision making components in the architecture. A close coupling of planning and time or resource scheduling is therefore possible within a system employing an activity based plan representation. 2 History and Technical Influences

This paper examines the issues that arise in the control of blackboard systems for applications with large and complicated search spaces by analyzing the evolution of blackboard control architectures. We feel that the issues addressed here apply more generally to AI application domains involving complex multi-dimensional search, in which control knowledge is as important to successful problem solving as domain knowledge. Evolution is viewed largely from the context of the Hearsay-II (HSII) speech understanding system. The appeal of the blackboard model is that it provides great flexibility in structuring problem solving. On the other hand, many of the features that are responsible for this flexibility make effective control difficult because they complicate the process of estimating the expected value of potential actions. Among the key themes in the evolution of blackboard control is the development of mechanisms that support more sophisticated goal-directed reasoning. In the basic co...

Sensor interpretation involves the determination of high-level explanations of sensor data. Blackboardbased interpretation systems have usually been limited to incremental hypothesize and test strategies for resolving uncertainty. We have developed a new interpretation framework that supports the use of more sophisticated strategies like differential diagnosis. The RESUN framework has two key components: an evidential representation that includes explicit, symbolic encodings of the sources of uncertainty (SOUs) in the evidence for hypotheses and a script-based, incremental control planner. Interpretation is viewed as an incremental process of gathering evidence to resolve particular sources of uncertainty. Control plans invoke actions that examine the symbolic SOUs associated with hypotheses and use the resulting information to post goals to resolve uncertainty. These goals direct the system to expand methods appropriate for resolving the current sources of uncertainty in the hypothese...

As part of research on sophisticated control for sensor interpretation, we have developed a planningbased control scheme for blackboard systems. A planner's goal/plan/subgoal structure provides explicit context information that can be used to index and apply large amounts of context-specific control knowledge. The key obstacle to using planning for the control of problem solvers is the need to deal with uncertain and dynamically changing situations without incurring unacceptable overhead. We have addressed these problems in several ways: our planner is script-based, planning and execution are interleaved, plans can invoke information gathering actions, plan refinement is controlled by plan-specific focusing heuristics, and the system's focus-of-attention can be dynamically shifted by the refocusing mechanism. Refocusing makes it possible to postpone focusing decisions and maintain the opportunistic control capabilities of conventional blackboard systems. Planning with refocusing result...

Gesture-Based Programming is a new paradigm to ease the burden of programming robots. By tapping in to the user's wealth of experience with contact transitions, compliance, uncertainty and operations sequencing, we hope to provide a more intuitive programming environment for complex, real-world tasks based on the expressiveness of non-verbal communication. A requirement for this to be accomplished is the ability to interpret gestures to infer the intentions behind them. As a first step toward this goal, this paper presents an application of distributed perception for inferring a user's intentions by observing tactile gestures. These gestures consist of sparse, inexact, physical "nudges" applied to the robot's end effector for the purpose of modifying its trajectory in free space. A set of independent agents - each with its own local, fuzzified, heuristic model of a particular trajectory parameter - observes data from a wrist force/torque sensor to evaluate the gestures. The agents then...

Designers routinely explain their designs to one another using sketches and verbal descriptions of behavior, both of which can be understood long before the device has been fully specified. But current design tools fail almost completely to support this sort of interaction, instead not only forcing designers to specify details of the design, but typically requiring that they do so by navigating a forest of menus and dialog boxes, rather than directly describing the behaviors with sketches and verbal explanations. We have created a prototype system, called assistance, capable of interpreting multimodal explanations for simple 2-D kinematic devices. The program generates a model of the events and the causal relationships between events that have been described via hand drawn sketches, sketched annotations, and verbal descriptions. Our goal is to make the designer's interaction with the computer more like interacting with another designer. This requires the ability not only to understand physical devices but also to understand the means by which the explanations of these devices are conveyed.

Goal relationships resulting from the initial data and subsequent processing can he used to dynamically construct a partial topology of the solution space based on what appear to be feasible solutions. This structure can be used to make control decisions that significantly reduce the amount of search required to solve a problem in a complex domain. We examine the utility of this approach in the context of a multi-level, cooperative knowledge source model of problem solving. We present a taxonomy of goal relationships for constructing partial topologies of the solution space and show that mechanisms using this information can be built as natural extensions of an integrated data-directed and goal directed archi tecture. Examples and performance results demonstrating how these additions improve the system's ability to evaluate potential activities are provided. 1

An application of distributed perception to a novel human/computer interface is presented. A multi-agent network has been applied to the task of modifying a robotic trajectory based on very sparse physical inputs from the user. The user conveys intentions by nudging the end effector, instrumented with a wrist force/torque sensor, in an intuitive manner. In response, each agent interprets these sparse inputs with the aid of a local, fuzzified, heuristic model of a particular parameter or trajectory shape. The agents then independently determine the confidence of their respective findings and distributed arbitration resolves the interpretation through voting. Table of Contents 1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 2. The Task . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 3. Distinguishing Force Features . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 4. Agen...