Intelligent Data Fusion and Multi-Agent Coordination for Target Allocation

Abstract

This paper addresses the fusion processing techniques for multi-sensor data perceived through the infrared sensors of military surveillance robots, and proposes their decision-theoretic coordination to effectively monitor multiple targets. To combine the multi-sensor data from the distributed battlefield robots, a set of fusion rules are used to formulate a combined prediction from the multi-source data. The possible type of a target is estimated through the fusion rules. For the identification of targets, agents need to keep track of targets for continuous situation awareness. The coordination of the agents with limited range of surveillance is indispensable for their successful monitoring of multiple targets. For dynamic and flexible coordination, our agents follow the decision-theoretic approach. We implement a military simulator to compare the capabilities of fusion processing and those of coordination, and conduct experiments with our framework in distributed and uncertain battlefield environments. The experimental results show that the fusion process of multi-sensor data from military robots can improve the performance of estimation of the type of a target, and our coordinated agents outperform agents using random strategy for their target selection in various military scenarios.

A multi-robot allocation model for multi-object based on Global Optimal Evaluation of Revenue

“…The MRS has been applied in workshop transportation, 1 intelligent warehousing, 2 emergency rescue, 3 and exploration of dangerous and unknown battlefield environment. 4 The reasonable assignment of tasks, the reduction of response time, and the combination of optimal paths will still be studied. According to the existing MRS, the solution of the multi-robot-multi-object-multi-task problem as assigning r robots to k desired object positions to perform n tasks at time t. There is rÂkÂn three-dimensional task solving set.…”