Yoonheui Kim

Effective Variants of the Max-Sum Algorithm for Radar Coordination and Scheduling

Solving a coordination problem in a decentralized environment requires a large amount of resources and thus exploiting the innate system structure and external information as much as possible is necessary for such a problem to be solved in a computationally effective manner. This work proposes new techniques for saving communication and computational resources when solving distributed constraint optimization problems using the Max-Sum algorithm in an environment where system hardware resources are clustered. These techniques facilitate effective problem solving through the use of a pre-computed policy and two phase propagation on Max-Sum algorithm, one inside the clustered resources and one among clustered resources. This approach shows equivalent quality to the standard Max-Sum algorithm while reducing communication requirements on average by50\% and computation resources by 5 to 30\% depending on the specific problem instance. These experiments were performed in a realistic setting involving the scheduling of a network of as many as 192 radars in 48 clusters.

Finding Minimum Data Requirements Using Pseudo-independence

In situations where Bayesian networks (BN) inferencing approximation is allowable, we show how to reduce the amount of sensory observations necessary and in a multi-agent context the amount of agent communication. To achieve this, we introduce Pseudo-Independence, a relaxed independence relation that quantitatively differentiates the various degrees of independence among nodes in a BN. We combine Pseudo-Independence with Context-Specific Independence to obtain a measure, Context-Specific Pseudo-Independence (CSPI), that determines the amount of required data that needs to be used to infer within the error bound. We then use a Conditional Probability Table-based generation search process that utilize CSPI to determine the minimal observation set. We present empirical results to demonstrate that bounded approximate inference can be made with fewer observations.