Victor R. Lesser

The Hearsay-II Speech-Understanding System: Integrating Knowledge to Resolve Uncertainty

The Hearsay-II system, developed during the DARPA-sponsored five-year speech-understanding research program, represents both a specific solution to the speech-understanding problem and a general framework for coordinating independent processes to achieve cooperative problem-solving behavior. As a computational problem, speech understanding reflects a large number of intrinsically interesting issues. Spoken sounds are achieved by a long chain of successive transformations, from intentions, through semantic and syntactic structuring, to the eventually resulting audible acoustic waves. As a consequence, interpreting speech means effectively inverting these transformations to recover the speakers intention from the sound. At each step in the interpretive process, ambiguity and uncertainty arise. The Hearsay-II problem-solving framework reconstructs an intention from hypothetical interpretations formulated at various levels of abstraction. In addition, it allocates limited processing resources first to the most promising incremental actions. The final configuration of the Hearsay-II system comprises problem-solving components to generate and evaluate speech hypotheses, and a focus-of-control mechanism to identify potential actions of greatest value. Many of these specific procedures reveal novel approaches to speech problems. Most important, the system successfully integrates and coordinates all of these independent activities to resolve uncertainty and control combinatorics. Several adaptations of the Hearsay-II framework have already been undertaken in other problem domains, and it is anticipated that this trend will continue; many future systems necessarily will integrate diverse sources of knowledge to solve complex problems cooperatively. Discussed in this paper are the characteristics of the speech problem in particular, the special kinds of problem-solving uncertainty in that domain, the structure of the Hearsay-II system developed to cope with that uncertainty, and the relationship between Hearsay-IIs structure and those of other speech-understanding systems. The paper is intended for the general computer science audience and presupposes no speech or artificial intelligence background.

A survey of multi-agent organizational paradigms

Many researchers have demonstrated that the organizational design employed by an agent system can have a significant, quantitative effect on its performance characteristics. A range of organizational strategies have emerged from this line of research, each with different strengths and weaknesses. In this article we present a survey of the major organizational paradigms used in multi-agent systems. These include hierarchies, holarchies, coalitions, teams, congregations, societies, federations, markets, and matrix organizations. We will provide a description of each, discuss their advantages and disadvantages, and provide examples of how they may be instantiated and maintained. This summary will facilitate the comparative evaluation of organizational styles, allowing designers to first recognize the spectrum of possibilities, and then guiding the selection of an appropriate organizational design for a particular domain and environment.

Trends in cooperative distributed problem solving

The authors present an overview of cooperative distributed problem solving (CDPS), an emerging research area that combines aspects of AI (artificial intelligence) and distributed processing. CDPS can be used to study how a loosely coupled network of sophisticated problem-solving nodes can solve a complex problem which consists of a set of interdependent subproblems. Subproblems arise because of spatial, temporal, and functional distribution of data, knowledge, and processing capabilities. Application areas include distributed interpretation, distributed planning and control, cooperating expert systems, and computer-supported human cooperation. The authors survey the important approaches and empirical investigations that have been developed. The approaches covered include negotiation, functionally accurate cooperation, organizational structuring, multiagent planning, sophisticated local control, and theoretical frameworks. >

Solving Distributed Constraint Optimization Problems Using Cooperative Mediation

Distributed Constraint Optimization Problems (DCDP) have, for a long time, been considered an important research area for multi-agent systems because a vast number of real-world situations can be modeled by them. The goal of many of the researchers interested in DCOP has been to find ways to solve them efficiently using fully distributed algorithms which are often based on existing centralized techniques. In this paper, we present an optimal, distributed algorithm called optimal asynchronous partial overlay (OptAPO) for solving DCOPs that is based on a partial centralization technique called cooperative mediation. The key ideas used by this algorithm are that agents, when acting as a mediator, centralize relevant portions of the DCDP, that these centralized subproblems overlap, and that agents increase the size of their subproblems as the problem solving unfolds. We present empirical evidence that shows that OptAPO performs better than other known, optimal DCOP techniques.

Functionally Accurate, Cooperative Distributed Systems

A new approach for structuring distributed processing systems, called functionally accurate, cooperative (FA/C), is proposed. The approach differs from conventional ones in its emphasis on handling distribution-caused uncertainty and errors as an integral part of the network problem-solving process. In this approach nodes cooperatively problem-solve by exchanging partial tentative results (at various levels of abstraction) within the context of common goals. The approach is especially suited to applications in which the data necessary to achieve a solution cannot be partitioned in such a way that a node can complete a task without seeing the intermediate state of task processing at other nodes. Much of the inspiration for the FA/C approach comes from the mechanisms used in knowledge-based artificial intelligence (Al) systems for resolving uncertainty caused by noisy input data and the use of approximate knowledge. The appropriateness of the FA/C approach is explored in three application domains: distributed interpretation, distributed network traffic-light control, and distributed planning. Additionally, the relationship between the approach and the structure of management organizations is developed. Finally, a number of current research directions necessary to more fully develop the FA/C approach are outlined. These research directions include distributed search, the integration of implicit and explicit forms of control, and distributed planning and organizational self-design.

Partial global planning: a coordination framework for distributed hypothesis formation

Partial global planning is used to provide a framework for coordinating multiple AI systems that are cooperating in a distributed sensor network. By combining a variety of coordination techniques into a single, unifying framework, partial global planning enables separate AI systems to reason about their roles and responsibilities as part of group problem solving, and to modify their planned processing and communication actions to act as a more coherent team. Partial global planning is uniquely suited for coordinating systems that are working in continuous, dynamic, and unpredictable domains because it interleaves coordination with action and allows systems to make effective decisions despite incomplete and possibly obsolete information about network activity. The authors implement and evaluate partial global planning in a simulated vehicle monitoring application and identifying promising extensions to the framework. >

Evolution of the GPGP/TÆMS domain-independent coordination framework

Generalized Partial Global Planning (GPGP) and its associated TAEMS hierarchical task network representation were developed as a domain-independent framework for coordinating the real-time activities of small teams of cooperative agents working to achieve a set of high-level goals. GPGPs development was influenced by two factors: one was to generalize and make domain-independent the coordination techniques developed in the Partial Global Planning (PGP) framework (this also involved our understanding that coordination activities could be separated from local agent control if an appropriate bi-directional interface could be established between them); the other was based on viewing agent coordination in terms of coordinating a distributed search of a dynamically evolving goal tree. Underlying these two influences was a desire to construct a model that could be used to explain and motivate the reasons for coordination among agents based on a quantitative view of task/subproblem dependency. Coordination of behaviors among agents requires three things: specification (creating shared goals), planning (subdividing goals into subgoals/tasks, i.e., creating the substructure of the evolving goal tree) and scheduling (assigning tasks to individual agents or groups of agents, creating shared plans and schedules and allocating resources). GPGP is primarily concerned with scheduling activities rather than the dynamic specification and planning of evolving activities (e.g., such as decomposing a high-level goal into a set of subgoals that if successfully achieved will solve the high-level goals).

Cooperative multiagent systems: a personal view of the state of the art

Scientific research and practice in multiagent systems focuses on constructing computational frameworks, principles, and models for how both small and large societies of intelligent, semiautonomous agents can interact effectively to achieve their goals. This article provides a personal view of the key application areas for cooperative multiagent systems, the major intellectual problems in building such systems, the underlying principles governing their design, and the major directions and challenges for future developments in this field.

Organization of the Hearsay II speech understanding system

Hearsay II (HSII) is a system currently under development at Carnegie-Mellon University to study the connected speech understanding problem. It is similar to Hearsay I (HSI) in that it is based on the hypothesize-and-test paradigm, using cooperating independent knowledge sources communicating with each other through a global data structure (blackboard). It differs in the sense that many of the limitations and shortcomings of HSI are resolved in HSII. The main new features of the Hearsay II system structure are: 1) the representation of knowledge as self-activating, asynchronous, parallel processes, 2) the representation of the partial analysis in a generalized three-dimensional network (the dimensions being level of representation (e.g., acoustic, phonetic, phonemic, lexical, syntactic), time, and alternatives) with contextual and structural support connections explicitly specified, 3) a convenient modular structure for incorporating new knowledge into the system at any level, and 4) a system structure suitable for execution on a parallel processing system. The main task domain under study is the retrieval of daily wire-service news stories upon voice request by the user. The main parametric representations used for this study are 1/3-octave filter-bank and linear-predictive coding (LPC)-derived vocal tract parameters [10], [11]. The acoustic segmentation and labeling procedures are parameter-independent [7]. The acoustic, phonetic, and phonological components [23] are feature-based rewriting rules which transform the segmental units into higher level phonetic units. The vocabulary size for the task is approximately 1200 words. This vocabulary information is used to generate word-level hypotheses from phonetic and surface-phonemic levels based on prosodic (stress) information. The syntax for the task permits simple English-like sentences and is used to generate hypotheses based on the probability of occurrence of that grammatical construct [19]. The semantic model is based on the news items of the day, analysis of the conversation, and the presence of certain content words in the partial analysis. This knowledge is to be represented as a production system. The system is expected to be operational on a 16-processor minicomputer system [3] being built at Carnegie-Mellon University. This paper deals primarily with the issues of the system organization of the HSII system.

Negotiating task decomposition and allocation using partial global planning

Abstract To coordinate as an effective team, cooperating problem solvers must negotiate over their use of local resources, information, and expertise. Sometimes they negotiate to decide which local problem-solving tasks to pursue, while at other times they negotiate over the decomposition and distribution of tasks. They might negotiate by sharing all of their information, or by exchanging proposals and counterproposals, or by working through an “arbitrator.” In general, negotiation is a complex process of improving agreement on common viewpoints or plans through the structured exchange of relevant information. In this paper, we describe how partial global planning provides a versatile framework for negotiating in different ways for different reasons, and we examine in detail its utility for negotiating over whether and how problem solvers should decompose and transfer tasks to improve group performance. Finally, we propose how our approach can be extended to capture even more fully the complexity, flexibility, and power of negotiation as a tool for coordinating distributed problem solvers.