Angle of Arrival Passive Location Algorithm Based on Proximal Policy Optimization

Abstract

Location technology is playing an increasingly important role in urban life. Various active and passive wireless positioning technologies for mobile terminals have attracted research attention. However, positioning signals experience serious interference in high-density residential areas or in the interior of large buildings. The main type of interference is that caused by non-line-of-sight (NLOS) propagation. In this paper, we present a new method for optimizing the angle of arrival (AOA) measurement to obtain high accuracy location results based on proximal policy optimization (PPO). PPO is a new family of policy gradient methods for reinforcement learning, which can be used to adjust the sampling data under different environments using stochastic gradient ascent. Therefore, PPO can correct the NLOS propagation errors to produce a clear AOA measurement data set without building an offline fingerprinting database. Then, we used the least square method to calculate the location. The simulation result shows that the AOA passive location algorithm based on PPO produced more accurate location information.

Advanced non-linear control based on artificial intelligence tuner for hand tremor suppression

“…As a result, it allows one sample to be used in numerous gradient ascent stages. By changing the new policy, the old and new policies will be separated, resulting in a higher variance of approximation and the old policy being updated to the new policy (Zhang et al, 2019). To achieve this goal, both policies should have a similar state transition function to ensure that the probability ratio is clipped to the region.…”

MS Location Estimation Based on the Artificial Bee Colony Algorithm

“…With the rapid development of deep learning, the performances of target positioning can be further improved by employing iterating calculations to reduce the NLOS errors [ 29 , 30 , 31 , 32 ]. In [ 29 ], hierarchical voting, known as the policy-based algorithm, was conducted before the measured signals enter the conventional filters.…”

“…The algorithm based on the deep neural network in [ 31 ] was capable of reaching convergence fast under noisy and varying environments. A gradient-related operation named proximal policy optimization (PPO) was executed on AOA measurement to correct the NLOS variances in the positioning results [ 32 ].…”

An Enhanced Indoor Positioning Technique Based on a Novel Received Signal Strength Indicator Distance Prediction and Correction Model

“…The distance measurement algorithm calculates the distance between the known beacon node and the unknown node connected to it, utilizing their communication link parameters. The main categories of distance measurement algorithms are the angle of arrival (AOA) based-algorithm [ 15 , 16 ], time of arrival (TOA) based-algorithm, time difference of arrival (TDOA) based-algorithm [ 17 , 18 ] and the received signal strength indication (RSSI) based-algorithm [ 19 , 20 , 21 , 22 , 23 ]. In the previously mentioned algorithms, the TOA, TDOA, and AOA need to correctly determine the distance between the unknown target node and the specified beacon node by using a high-complexity algorithm that requires high energy consumption and additional hardware.…”