Constraint Programming (CP) has proved an effective paradigm to model and solve difficult combinatorial satisfaction and optimisation problems from disparate domains. Many such problems arising from the commercial world are permeated by data uncertainty. Existing CP approaches that accommodate uncertainty are less suited to uncertainty arising due to incomplete and erroneous data, because they do not build reliable models and solutions guaranteed to address the user's genuine problem as she perceives it. Other fields such as reliable computation offer combinations of models and associated methods to handle these types of uncertain data, but lack an expressive framework characterising the resolution methodology independently of the model. We present a unifying framework that extends the CP formalism in both model and solutions, to tackle ill-defined combinatorial problems with incomplete or erroneous data. The certainty closure framework brings together modelling and solving methodologies from different fields into the CP paradigm to provide reliable and efficient approches for uncertain constraint problems. We demonstrate the applicability of the framework on a case study in network diagnosis. We define resolution forms that give generic templates, and their associated operational semantics, to derive practical solution methods for reliable solutions.

This paper presents a model and implementation techniques for speeding up constraint propagation. Three fundamental approaches to improving constraint propagation based on propagators as implementations of constraints are explored: keeping track of which propagators are at fixpoint, choosing which propagator to apply next, and how to combine several propagators for the same constraint. We show how idempotence reasoning and events help track fixpoints more accurately. We improve these methods by using them dynamically (taking into account current domains to improve accuracy). We define priority-based approaches to choosing a next propagator and show that dynamic priorities can improve propagation. We illustrate that the use of multiple propagators for the same constraint can be advantageous with priorities, and introduce staged propagators that combine the effects of multiple propagators with priorities for greater efficiency.

Efficient representations and solutions for large decision problems with continuous and discrete variables are among the most important challenges faced by the designers of automated decision support systems. In this paper, we describe a novel hybrid factored Markov decision process (MDP) model that allows for a compact representation of these problems, and a new hybrid approximate linear programming (HALP) framework that permits their efficient solutions. The central idea of HALP is to approximate the optimal value function by a linear combination of basis functions and optimize its weights by linear programming. We analyze both theoretical and computational aspects of this approach, and demonstrate its scale-up potential on several hybrid optimization problems.

Multimodal conversational interfaces provide a natural means for users to communicate with computer systems through multiple modalities such as speech and gesture. To build effective multimodal interfaces, automated interpretation of user multimodal inputs is important. Inspired by the previous investigation on cognitive status in multimodal human machine interaction, we have developed a greedy algorithm for interpreting user referring expressions (i.e., multimodal reference resolution). This algorithm incorporates the cognitive principles of Conversational Implicature and Givenness Hierarchy and applies constraints from various sources (e.g., temporal, semantic, and contextual) to resolve references. Our empirical results have shown the advantage of this algorithm in efficiently resolving a variety of user references. Because of its simplicity and generality, this approach has the potential to improve the robustness of multimodal input interpretation.

In this paper, we present the partitioning of mutual-exclusion (mutex) constraints in temporal planning problems and its implementation in the SGPlan4 planner. Based on the strong locality of mutex constraints observed in many benchmarks of the Fourth International Planning Competition (IPC4), we propose to partition the constraints of a planning problem into groups based on their subgoals. Constraint partitioning leads to significantly easier subproblems that are similar to the original problem and that can be efficiently solved by the same planner with some modifications to its objective function. We present a partition-and-resolve strategy that looks for locally optimal subplans in constraint-partitioned temporal planning subproblems and that resolves those inconsistent global constraints across the subproblems. We also discuss some implementation details of SGPlan4, which include the resolution of violated global constraints, techniques for handling producible resources, landmark analysis, path finding and optimization, search-space reduction, and modifications of Metric-FF when used as a basic planner in SGPlan4. Last, we show results on the sensitivity of each of these techniques in quality-time trade-offs and experimentally demonstrate that SGPlan4 is effective for solving the IPC3 and IPC4 benchmarks.

Code optimization and high level synthesis can be posed as constraint satisfaction and optimization problems, such as graph coloring used in register allocation. Graph coloring is also used to model more traditional CSPs relevant to AI, such as planning, time-tabling and scheduling. Provably optimal solutions may be desirable for commercial and defense applications. Additionally, for applications such as register allocation and code optimization, naturally-occurring instances of graph coloring are often small and can be solved optimally. A recent wave of improvements in algorithms for Boolean satisfiability (SAT) and 0-1 Integer Linear Programming (ILP) suggests generic problem-reduction methods, rather than problem-specific heuristics, because (1) heuristics may be upset by new constraints, (2) heuristics tend to ignore structure, and (3) many relevant problems are provably inapproximable. Problem reductions often lead to highly symmetric SAT instances, and symmetries are known to slow down SAT solvers. In this work, we compare several avenues for symmetry breaking, in particular when certain kinds of symmetry are present in all generated instances. Our focus on reducing CSPs to SAT allows us to leverage recent dramatic improvement in SAT solvers and automatically benefit from future progress. We can use a variety of black-box SAT solvers without modifying their source code because our symmetry-breaking techniques are static, i.e., we detect symmetries and add symmetry breaking predicates (SBPs) during pre-processing. An important result of our work is that among the types of instance-independent SBPs we studied and their combinations, the simplest and least complete constructions are the most effective. Our experiments also clearly indicate that instance-independent symmetries should mostly be processed together with instance-specific symmetries rather than at the specification level, contrary to what has been suggested in the literature.

Distributed Constraint Satisfaction (DCSP) has long been considered an important problem in multi-agent systems research. This is because many real-world problems can be represented as constraint satisfaction and these problems often present themselves in a distributed form. In this article, we present a new complete, distributed algorithm called asynchronous partial overlay (APO) for solving DCSPs that is based on a cooperative mediation process. The primary ideas behind this algorithm are that agents, when acting as a mediator, centralize small, relevant portions of the DCSP, that these centralized subproblems overlap, and that agents increase the size of their subproblems along critical paths within the DCSP as the problem solving unfolds. We present empirical evidence that shows that APO outperforms other known, complete DCSP techniques.

A delta-model is a satisfying assignment of a Boolean formula for which any small alteration, such as a single bit flip, can be repaired by flips to some small number of other bits, yielding a new satisfying assignment. These satisfying assignments represent robust solutions to optimization problems (e.g., scheduling) where it is possible to recover from unforeseen events (e.g., a resource becoming unavailable). The concept of delta-models was introduced by Ginsberg, Parkes and Roy (AAAI 1998) , where it was proved that finding delta-models for general Boolean formulas is NP-complete. In this paper, we extend that result by studying the complexity of finding delta-models for classes of Boolean formulas which are known to have polynomial time satisfiability solvers. In particular, we examine 2-SAT, Horn-SAT, Affine-SAT, dual-Horn-SAT, 0-valid and 1-valid SAT. We see a wide variation in the complexity of finding delta-models, e.g., while 2-SAT and Affine-SAT have polynomial time tests for delta-models, testing whether a Horn-SAT formula has one is NP-complete.

In recent years, CP-nets have emerged as a useful tool for supporting preference elicitation, reasoning, and representation. CP-nets capture and support reasoning with qualitative conditional preference statements, statements that are relatively natural for users to express. In this paper, we extend the CP-nets formalism to handle another class of very natural qualitative statements one often uses in expressing preferences in daily life - statements of relative importance of attributes. The resulting formalism, TCP-nets, maintains the spirit of CP-nets, in that it remains focused on using only simple and natural preference statements, uses the ceteris paribus semantics, and utilizes a graphical representation of this information to reason about its consistency and to perform, possibly constrained, optimization using it. The extra expressiveness it provides allows us to better model tradeoffs users would like to make, more faithfully representing their preferences.

Several special tracks included a significant number of presentations. Zdravko Markov and Larry Holder, was the most extensive, with 18 papers presented of the 35 submitted. The conference continues by Vasile Rus, was the second largest. The last few years have seen a significant reception. This year's conference received version for publication consideration A best paper award was presented to Jeffrey A. Coble, Diane J. Cook, and The program included a general session Lawrence B. Holder of the University with many excellent papers spanning of Texas at Arlington for their paper titled a broad range of AI research areas "Structure Discovery in Sequentially and covering traditional topics such as Connected Data."