Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 2018

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: error mitigation

Sortuj według:

Ogranicz wyniki do:

Error mitigation algorithm based on bidirectional fitting method for collision avoidance of Unmanned Surface Vehicle

Song L., Chen Z., Mao Y., Dong Z., Xiang Z.

Polish Maritime Research

2018

nr 4

13--20

Radars and sensors are essential devices for an Unmanned Surface Vehicle (USV) to detect obstacles. Their precision has improved significantly in recent years with relatively accurate capability to locate obstacles. However, small detection errors in the estimation and prediction of trajectories of obstacles may cause serious problems in accuracy, thereby damaging the judgment of USV and affecting the effectiveness of collision avoidance. In this study, the effect of radar errors on the prediction accuracy of obstacle position is studied on the basis of the autoregressive prediction model. The cause of radar error is also analyzed. Subsequently, a bidirectional adaptive filtering algorithm based on polynomial fitting and particle swarm optimization is proposed to eliminate the observed errors in vertical and abscissa coordinates. Then, simulations of obstacle tracking and prediction are carried out, and the results show the validity of the algorithm. Finally, the method is used to simulate the collision avoidance of USV, and the results show the validity and reliability of the algorithm.

Ensembling a linear regression model with an error mitigation component

Nowosielski A., Kowalski P. A., Kulczycki P.

Journal of Automation Mobile Robotics and Intelligent Systems

2018

Vol. 12, No. 1

40--43

This paper presents a proposal of a model error mitigation technique based on the error distribution analysis of the original model and creatng the additional model that tempers the error impact in particular domain areas identified as the most sensitive. both models are then combined into single ensemble model. The idea is demonstrated on the trivial two-dimensional linear regression model.