Abstract
To provide high-quality location-based services in the era of the Internet of Things, visible light positioning (VLP) is considered a promising technology for indoor positioning. In this paper, we study a multi-photodiodes (multi-PDs) three-dimensional (3D) indoor VLP system enhanced by reinforcement learning (RL), which can realize accurate positioning in the 3D space without any off-line training. The basic 3D positioning model is introduced, where without height information of the receiver, the initial height value is first estimated by exploring its relationship with the received signal strength (RSS), and then, the coordinates of the other two dimensions (i.e., X and Y in the horizontal plane) are calculated via trilateration based on the RSS. Two different RL processes, namely RL1 and RL2, are devised to form two methods that further improve horizontal and vertical positioning accuracy, respectively. A combination of RL1 and RL2 as the third proposed method enhances the overall 3D positioning accuracy. The positioning performance of the four presented 3D positioning methods, including the basic model without RL (i.e., Benchmark) and three RL based methods that run on top of the basic model, is evaluated experimentally. Experimental results verify that obviously higher 3D positioning accuracy is achieved by implementing any proposed RL based methods compared with the benchmark. The best performance is obtained when using the third RL based method that runs RL2 and RL1 sequentially. For the testbed that emulates a typical office environment with a height difference between the receiver and the transmitter ranging from 140 cm to 200 cm, an average 3D positioning error of 2.6 cm is reached by the best RL method, demonstrating at least 20% improvement compared to the basic model without performing RL.
Highlights
The developments of location-based mobile services and the Internet of Things urgently need stable and precise indoor positioning technologies [1]
In the single-PD system, 3D positioning has been achieved by combining information from both the PD and the other hardware either at the receiver or at the transmitter, which is not necessarily simpler than the multiple-PD system from the system complexity perspective. 3D positioning based on a low complexity receiver with one PD only has been proposed, which has additional requirements for the radiation patterns or geometric arrangement of LEDs to avoid ambiguity in height estimation [16,17]. 3D visible light positioning (VLP)
After taking an action that modifies Rec and h, the 3D coordinates of all PDs are obtained via trilateration and used to calculate its Reward based on a new Edis according to Equation (9)
Summary
The developments of location-based mobile services and the Internet of Things urgently need stable and precise indoor positioning technologies [1]. 3D VLP systems using multiple PDs have been proposed, in which the spatial or angular diversity of PDs are explored to estimate the 3D position of the receiver [18,19,20] Though it needs more PDs at the receiver, it does not have any special requirement for the transmitter [16,17] and has shown the potential to reduce the number of LEDs for a simpler transmitter [13]. A 3D VLP system using multiple PDs and reinforcement learning is proposed which realizes high accuracy for 3D positioning without needs of data for off-line training.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have