Embedded systems consisting of collaborating agents capable of interacting with their environment are becoming ubiquitous. It is crucial for these systems to be able to adapt to the dynamic and uncertain characteristics of an open environment. In this paper, we argue that multiagent meta-level control (MMLC) is an effective way to determine when this adaptation process should be done and how much effort should be invested in adaptation as opposed to continuing with the current action plan. We describe a reinforcement learning based approach to learn decentralized meta-control policies offline. We then propose to use the learned reward model as input to a global optimization algorithm to avoid conflicting meta-level decisions between coordinating agents. Our initial experiments in the context of NetRads, a multiagent tornado tracking application show that MMLC significantly improves performance in a 3-agent network.

As a robot formation increases in size or explores places where it is difficult for a human operator to interact, autonomous control becomes critical. We propose a distributed autonomous method for evaluating properties of multi-robot systems, and then discuss how this information can be applied to improve performance with respect to a given operation. We present this as an extension of our previous work on robot formations; however, the techniques described could be adapted to other multi-robot systems.

Auctions are promising decentralized methods for teams of agents to allocate and re-allocate tasks among themselves in dynamic, partially known and time-constrained domains with positive or negative synergies among tasks. Auction-based coordination systems are easy to understand, simple to implement and broadly applicable. They promise to be efficient both in communication (since agents communicate only essential summary information) and in computation (since agents compute their bids in parallel). Artificial intelligence research has explored auction-based coordination systems since the early work on contract networks, mostly from an experimental perspective. This overview paper describes our recent progress towards creating a framework for the design and analysis of cooperative auctions for agent coordination.

The selection of the action to do next is one of the central problems faced by autonomous agents. In AI, three approaches have been used to address this problem: the programming-based approach, where the agent controller is given by the programmer, the learning-based approach, where the controller is induced from experience via a learning algorithm, and the model-based approach, where the controller is derived from a model of the problem. Planning in AI is best conceived as the model-based approach to action selection. The models represent the initial situation, actions, sensors, and goals. The main challenge in planning is computational, as all the models, whether accommodating feedback and uncertainty or not, are intractable in the worst case. In this article, I review some of the models considered in current planning research, the progress achieved in solving these models, and some of the open problems.

Decentralized agent groups typically require complex mechanisms to accomplish coordinated tasks. In contrast, biological systems can achieve intelligent group behaviors with each agent performing simple sensing and actions. We summarize our recent papers on a biologically-inspired control framework for multi-agent tasks that is based on a simple and iterative control law. We theoretically analyze important aspects of this decentralized approach, such as the convergence and scalability, and further demonstrate how this approach applies to real-world applications with a diverse set of multi-agent applications. These results provide a deeper understanding of the contrast between centralized and decentralized algorithms in multi-agent tasks and autonomous robot control.

Correcting recognition errors is often necessary in a speech interface. These errors not only reduce users' overall entry rate, but can also lead to frustration. While making fewer recognition errors is undoubtedly helpful, facilities for supporting user-guided correction are also critical. We explore how to better support user corrections using Parakeet — a continuous speech recognition system for mobile touch-screen devices. Parakeet's interface is designed for easy error correction on a handheld device. Users correct errors by selecting alternative words from a word confusion network and by typing on a predictive software keyboard. Our interface design was guided by computational experiments and used a variety of information sources to aid the correction process. In user studies, participants were able to write text effectively despite sometimes high initial recognition error rates. Using Parakeet as an example, we discuss principles we found were important for building an effective speech correction interface.

Modern techniques for representing games and computing their Nash equilibria are approaching the point where they can be used to analyze market games. We demonstrate this by showing how the equilibria of different position auction mechanisms can be tractably identified using these techniques. These results enable detailed and quantitative comparisons of the different auction mechanisms — in terms of both efficiency and revenue — under different preference models and equilibrium selection criteria.

As computer architectures become increasingly complex, hand-tuning compiler heuristics becomes increasingly tedious and time consuming for compiler developers. This paper presents a case study that uses a genetic algorithm to learn a compiler policy. The target policy implicitly balances communication and contention among processing elements of the TRIPS processor, a physically realized prototype chip. We learn specialized policies for individual programs as well as general policies that work well across all programs. We also employ a two-stage method that first classifies the code being compiled based on salient characteristics, and then chooses a specialized policy based on that classification. This work is particularly interesting for the AI community because it 1) emphasizes the need for increased collaboration between AI researchers and researchers from other branches of computer science and 2) discusses a machine learning setup where training on the custom hardware requires weeks of training, rather than the more typical minutes or hours.

The bare minimum lexical resource required to translate between a pair of languages is a translation dictionary. Unfortunately, dictionaries exist only between a tiny fraction of the 49 million possible language-pairs making machine translation virtually impossible between most of the languages. This paper summarizes the last four years of our research motivated by the vision of panlingual communication. Our research comprises three key steps. First, we compile over 630 freely available dictionaries over the Web and convert this data into a single representation – the translation graph. Second, we build several inference algorithms that infer translations between word pairs even when no dictionary lists them as translations. Finally, we run our inference procedure offline to construct PANDICTIONARY– a sense-distinguished, massively multilingual dictionary that has translations in more than 1000 languages. Our experiments assess the quality of this dictionary and find that we have 4 times as many translations at a high precision of 0.9 compared to the English Wiktionary, which is the lexical resource closest to PANDICTIONARY.

The problem of dividing a sequence of values into segments occurs in database systems, information retrieval, and knowledge management. The challenge is to select a finite number of boundaries for the segments so as to optimize an objective error function defined over those segments. Although this optimization problem can be solved in polynomial time, the algorithm which achieves the minimum error does not scale well, hence it is not practical for applications with massive data sets. There is considerable research with numerous approximation and heuristic algorithms. Still, none of those approaches has resolved the quality-efficiency tradeoff in a satisfactory manner. In (Halim, Karras, and Yap 2009), we obtain near linear time algorithms which achieve both the desired scalability and near-optimal quality, thus dominating earlier approaches. In this paper, we show how two ideas from artificial intelligence, an efficient local search and recombination of multiple solutions reminiscent of genetic algorithms, are combined in a novel way to obtain state of the art histogram construction algorithms.