Research Article
Target Tracking Based on DDPG in Wireless Sensor Network
@INPROCEEDINGS{10.1007/978-3-030-57115-3_22, author={Yinhua Liao and Qiang Liu}, title={Target Tracking Based on DDPG in Wireless Sensor Network}, proceedings={Bio-inspired Information and Communication Technologies. 12th EAI International Conference, BICT 2020, Shanghai, China, July 7-8, 2020, Proceedings}, proceedings_a={BICT}, year={2020}, month={8}, keywords={Wireless sensor network Target tracking Collaborative perception Deep deterministic policy gradient}, doi={10.1007/978-3-030-57115-3_22} }- Yinhua Liao
Qiang Liu
Year: 2020
Target Tracking Based on DDPG in Wireless Sensor Network
BICT
Springer
DOI: 10.1007/978-3-030-57115-3_22
Abstract
For target tracking in mission critical sensors and sensor networks (MC-SSN), the contribution of the measured value of each sensor node to the data fusion center is different, so better weighted node fusion and scheduling node participation in tracking can obtain better tracking performance. In this paper, to address this problem and fully utilize the network transmission capability, we proposed a collaborative perception and intelligent scheduling to jointly optimize system responding latency and tracking accuracy while guaranteeing low energy consumption. Based on the unreliable historical tracking data, we formulate the joint optimization problem as the infinite horizon Markov Decision Process (MDP), we propose an intelligent collaboration scheme based on the deep deterministic policy gradient (DDPG) approach to perform the optimal tracking with low energy consumption and high tracking accuracy.
