Adaptive Navigation Algorithm Research Articles

Deep Reinforcement Learning for Robotic Approaching Behavior Influenced by User Activity and Disengagement

AbstractA robot intended to monitor human behavior must account for the user’s reactions to minimize his/her perceived discomfort. The possibility of learning user interaction preferences and changing the robot’s behavior accordingly may positively impact the perceived quality of the interaction with the robot. The robot should approach the user without causing any discomfort or interference. In this work, we contribute and implement a novel Reinforcement Learning (RL) approach for robot navigation toward a human user. Our implementation is a proof-of-concept that uses data gathered from real-world experiments to show that our algorithm works on the kind of data that it would run on in a realistic scenario. To the best of our knowledge, our work is one of the first attempts to provide an adaptive navigation algorithm that uses RL to account for non-deterministic phenomena.

GNSS 불용 구간 내 특수 임무용 드론 자세 보정을 위한 영상 정보 기반 적응형 항법 알고리즘

In the field of UAV (Unmanned Aerial Vehicle), drone is noticed that it can replace human role in unknown/hazardous area. Drone’s position is calculated with GNSS (Global Navigation Satellite System) and INS (Inertial Navigation System), however, environment like under bridge, GNSS signal is not reliable, which makes INS diverge. In this situation, drone’s orientation is important for suppressing the divergence of position by INS. Roll and pitch angle can be estimated by employing G-slave mode attitude compensation algorithm. However, yaw angle cannot be estimated well. In this paper, we propose indirect EKF (Extended Kalman Filter) based adaptive navigation algorithm that uses line information from image. In the algorithm, we calculate the relative yaw angle from line information. To get reliable yaw angle, we introduce angle compensation algorithm that corrects the distorted line information by roll and pitch angle. Furthermore, we propose outlier mitigation and adaptation rule based on distance between inlier-outlier features and the number of features for classifying the reliability of the yaw information from the image. Through the simulation, it is confirmed that the proposed algorithm estimates yaw angle sufficiently. After that, we conduct experiment and it is validated that proposed algorithm can reduced heading error with 25.32%.

Adaptive Navigation Algorithm with Deep Learning for Autonomous Underwater Vehicle.

Precise navigation is essential for autonomous underwater vehicles (AUVs). The measurement deviation of the navigation sensors, especially the microelectromechanical systems (MEMS) sensors, is a crucial factor that affects the localization accuracy. Deep learning is a novel method to solve this problem. However, the calculation cycle and robustness of the deep learning method may be insufficient in practical application. This paper proposes an adaptive navigation algorithm with deep learning to address these questions and realize accurate navigation. Firstly, this algorithm uses deep learning to generate low-frequency position information to correct the error accumulation of the navigation system. Secondly, the χ2 rule is selected to judge if the Doppler velocity log (DVL) measurement fails, which could avoid interference from DVL outliers. Thirdly, the adaptive filter, based on the variational Bayesian (VB) method, is employed to estimate the navigation information simultaneous with the measurement covariance, improving navigation accuracy even more. The experimental results, based on AUV field data, show that the proposed algorithm could realize robust navigation performance and significantly improve position accuracy.

Adaptive Navigation Algorithm Under Abnormal Measurements in Libration-Point Mission

This paper investigates X-ray pulsar navigation for earth–moon libration-point mission. A comprehensive analysis shows that abnormal measurements are inevitable and bring quite adverse effects for navigation results. To approach this problem, a new algorithm called robust square-root cubature Kalman filter is proposed. An innovation-based adaptive scale factor is introduced to adjust measurement noise covariance so that the adverse effects of abnormal measurements can be suppressed. Effectiveness of the proposed method is demonstrated in simulation results.