Abstract
In TDOA passive location tasks, the geometric configuration can greatly affect the positioning precision due to the complicated characteristics of electromagnetic environment. How to find an appropriate path to a good geometry to locate the transmitter accurately is vital in practical location tasks. This paper proposes a novel geometry optimization method based on deep reinforcement learning. In the proposed method, stations are regarded as mobile agents that can receive wireless signals decide where to go. All agents are controlled by an actor-critic learner, which is trained on the experiences collected from executing the TDOA location task repeatedly. To evaluate the trained agents, a TDOA location simulator environment with complex electromagnetic characteristics is developed. The empirical results show that, the learner mastered useful strategies and navigated to optimal geometric configurations efficiently. A visual depiction of highlights of the learner’s behavior in TDOA passive location tasks can be viewed in the video provided in the supplementary material.
Highlights
Passive location techniques are used for various scenarios, such as telecommunication pseudo base station discovery, aviation interference investigation, etc
This paper provides a new perspective for geometric optimization, i.e., a sequential decision-making problem which needs to specify a path that navigates to an optimal geometry in a complex electromagnetic environment
Under the framework of deep reinforcement learning (DRL), all stations are regarded as mobile agents
Summary
Passive location techniques are used for various scenarios, such as telecommunication pseudo base station discovery, aviation interference investigation, etc. Passive location systems based on time differences of arrivals (TDOA) is widely used for its simplicity and crypticity. In a TODA location system, a number of spatially separated sensors capture the signals emitted by the transmitter and estimate time differences of arrivals to locate the transmitter [1]–[4]. Some existing studies tried to obtain general principles of geometric configurations from massive experiments [6], [7]. From the signals received by station i, j (i = j), i.e., zi and zj, the time difference of arrival ij can be obtained through correlation function i,j = Corr(zi, zj),
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
