離散周辺防衛問題における逐次捕捉のための分散スパイク学習フレームワーク

原文アブストラクト

This paper proposes a novel Decentralized Spike-based Learning (DSL) framework for the discrete Perimeter Defense Problem (d-PDP). A team of defenders is operating on the perimeter to protect the circular territory from radially incoming intruders. At first, the d-PDP is formulated as a spatio-temporal multi-task assignment problem (STMTA). The problem of STMTA is then converted into a multi-label learning problem to obtain labels of segments that defenders have to visit in order to protect the perimeter. The DSL framework uses a Multi-Label Classifier using Synaptic Efficacy Function spiking neuRON (MLC-SEFRON) network for deterministic multi-label learning. Each defender contains a single MLC-SEFRON network. Each MLC-SEFRON network is trained independently using input from its own perspective for decentralized operations. The input spikes to the MLC-SEFRON network can be directly obtained from the spatio-temporal information of defenders and intruders without any extra pre-processing step. The output of MLC-SEFRON contains the labels of segments that a defender has to visit in order to protect the perimeter. Based on the multi-label output from the MLC-SEFRON a trajectory is generated for a defender using a Consensus-Based Bundle Algorithm (CBBA) in order to capture the intruders. The target multi-label output for training MLC-SEFRON is obtained from an expert policy. Also, the MLC-SEFRON trained for a defender can be directly used for obtaining labels of segments assigned to another defender without any retraining. The performance of MLC-SEFRON has been evaluated for full observation and partial observation scenarios of the defender. The overall performance of the DSL framework is then compared with expert policy along with other existing learning algorithms. The scalability of the DSL has been evaluated using an increasing number of defenders.