Military course-of-action (COA) diagrams are used to depict battle scenarios and include thousands of unique symbols, complete with additional textual and designator modifiers. We have created a real-time sketch recognition interface that recognizes 485 freely-drawn military course-of-action sym- bols. When the variations (not allowable by other systems) are factored in, our system is several orders of magnitude larger than the next biggest system. On 5,900 hand-drawn symbols, the system achieves an accuracy of 90% when con- sidering the top 3 interpretations and requiring every aspect of the shape (variations, text, symbol, location, orientation) to be correct.

We present a highly efficient incremental algorithm for propagating bounded knapsack constraints. Our algorithm is based on the sublinear filtering algorithm for binary knapsack constraints by Katriel et al. and achieves similar speed-ups of one to two orders of magnitude when compared with its linear-time counterpart. We also show that the representation of bounded knapsacks as binary knapsacks leads to ineffective filtering behavior. Experiments on standard knapsack benchmarks show that the new algorithm significantly outperforms existing methods for handling bounded knapsack constraints.

Existing controller-based approaches for centralized and decentralized POMDPs are based on automata with output known as Moore machines. In this paper, we show that several advantages can be gained by utilizing another type of automata, the Mealy machine. Mealy machines are more powerful than Moore machines, provide a richer structure that can be exploited by solution methods, and can be easily incorporated into current controller-based approaches. To demonstrate this, we adapted some existing controller-based algorithms to use Mealy machines and obtained results on a set of benchmark domains. The Mealy-based approach always outperformed the Moore-based approach and often outperformed the state-of-the-art algorithms for both centralized and decentralized POMDPs. These findings provide fresh and general insights for the improvement of existing algorithms and the development of new ones.

This paper investigates search techniques for multi-agent settings in which the most suitable agent, according to given criteria, needs to be found. In particular, it considers the case where the searching agent incurs a cost for learning the value of an agent and the goal is to minimize the expected overall cost of search by iteratively increasing the extent of search. This kind of search is applicable to various domains, including auctions, first responders, and sensor networks. Using an innovative transformation of the extents-based sequence to a probability-based one, the optimal sequence is proved to consist of either a single search iteration or an infinite sequence of increasing search extents. This leads to a simplified characterization of the the optimal search sequence from which it can be derived. This method is also highly useful for legacy economic-search applications, where all agents are considered suitable candidates and the goal is to optimize the search process as a whole. The effectiveness of the method for both best-valued search and economic search is demonstrated numerically using a synthetic environment.

We consider how to learn Hierarchical Task Networks (HTNs) for planning problems in which both the quality of solution plans generated by the HTNs and the speed at which those plans are found is important. We describe an integration of HTN Learning with Reinforcement Learning to both learn methods by analyzing semantic annotations on tasks and to produce estimates of the expected values of the learned methods by performing Monte Carlo updates. We performed an experiment in which plan quality was inversely related to plan length. In two planning domains, we evaluated the planning performance of the learned methods in comparison to two state-of-the-art satisficing classical planners, FastForward and SGPlan6, and one optimal planner, HSP*. The results demonstrate that a greedy HTN planner using the learned methods was able to generate higher quality solutions than SGPlan6 in both domains and FastForward in one. Our planner, FastForward, and SGPlan6 ran in similar time, while HSP* was exponentially slower.

The field of multi-robot coordination, specifically robot formation control, is rapidly expanding, with many applications proposed. In our previous work, we considered the problem of establishing and maintaining a formation of robots given an already connected network. We now propose a distributed auction-based method to autonomously initialize and reorganize the network structure of a formation of robots.

We present an algorithm that exploits the complimentary benefits of best-first search (BFS) and depth-first search (DFS) by performing limited DFS lookaheads from the frontier of BFS. We show that this continuum requires significantly less memory than BFS. In addition, a time speedup is also achieved when choosing the lookahead depth correctly. We demonstrate this idea for breadth-first search and for A*. Additionally, we show that when using inconsistent heuristics, Bidirectional Pathmax (BPMX), can be implemented very easily on top of the lookahead phase. Experimental results on several domains demonstrate the benefits of all our ideas.

We present an instance-based, online method for learning action models in unanticipated, relational domains. Our algorithm memorizes pre- and post-states of transitions an agent encounters while experiencing the environment, and makes predictions by using analogy to map the recorded transitions to novel situations. Our algorithm is implemented in the Soar cognitive architecture, integrating its task-independent episodic memory module and analogical reasoning implemented in procedural memory. We evaluate this algorithm’s prediction performance in a modified version of the blocks world domain and the taxi domain. We also present a reinforcement learning agent that uses our model learning algorithm to significantly speed up its convergence to an optimal policy in the modified blocks world domain.

Building an intelligent agent, which simulates human-level learning appropriate for learning math, science, or a second language, could potentially benefit both education in understanding human learning, and artificial intelligence in creating human-level intelligence. Recently, we have proposed an efficient approach to acquiring procedural knowledge using transfer learning. However, it operated as a separate module. In this paper, we describe how to integrate this module into a machine-learning agent, SimStudent, that learns procedural knowledge from examples and through problem solving. We illustrate this method in the domain of algebra, after which we consider directions for future research in this area.

Good and generous knowledge sources, reliable and efficient induction patterns, and automatic and controllable quality assertion approaches are three critical issues to commonsense knowledge (CSK) acquisition. This paper employs Open Mind Common Sense (OMCS), a volunteers-contributed CSK database, to study the first and the third issues. For those stylized CSK, our result shows that over 40% of CSK for four predicate types in OMCS can be found in the web, which contradicts to the assumption that CSK is not communicated in texts. Moreover, we propose a commonsense knowledge classifier trained from OMCS, and achieve high precision in some predicate types, e.g., 82.6% in HasProperty. The promising results suggest new ways of analyzing and utilizing volunteer-contributed knowledge to design systems automatically mining commonsense knowledge from the web.