A Velocity Prediction Method based on Self-Learning Multi-Step Markov Chain
| Affiliation auteurs | Affiliation ok |
| Titre | A Velocity Prediction Method based on Self-Learning Multi-Step Markov Chain |
| Type de publication | Conference Paper |
| Year of Publication | 2019 |
| Auteurs | Zhou Y, Ravey A, Pera M-C |
| Conference Name | 45TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY (IECON 2019) |
| Publisher | IEEE; Univ Nova Lisboa; IEEE Ind Elect Soc |
| Conference Location | 345 E 47TH ST, NEW YORK, NY 10017 USA |
| ISBN Number | 978-1-7281-4878-6 |
| Mots-clés | Markov chain, Self-learning, Velocity Prediction |
| Résumé | This paper presents a vehicle speed prediction method based on the self-learning multi-step Markov Chain. By estimating the transition probability matrices with the online measured data, the proposed method can better adapt to the novel driving conditions. Through three representative case studies, its effectiveness and the advantages over the conventional Markov predictor under multiple driving scenarios are verified. Simulation results show that in dealing with the newly encountered driving conditions, the proposed approach can reduce the average prediction error by 25.70% compared to the conventional Markov predictor. Besides, the maximum online computation time of the proposed method is 7.021ms, indicating its real-time practicality. |